[PATCH 00/10] readahead cleanups and interleaved readahead take 4

[PATCH 00/10] readahead cleanups and interleaved readahead take 4

[Fengguang Wu]

Andrew,

Here are some more readahead related cleanups and updates.

smaller file_ra_state:
	[PATCH 01/10] readahead: compacting file_ra_state                             
	[PATCH 02/10] readahead: mmap read-around simplification                      
	[PATCH 03/10] readahead: combine file_ra_state.prev_index/prev_offset into prev_pos

Interleaved readahead:
	[PATCH 04/10] radixtree: introduce radix_tree_scan_hole()                     
	[PATCH 05/10] readahead: basic support of interleaved reads                   

Readahead cleanups:
	[PATCH 06/10] readahead: remove several readahead macros                      
	[PATCH 07/10] readahead: remove the limit max_sectors_kb imposed on max_readahead_kb
	[PATCH 08/10] readahead: remove the local copy of ra in do_generic_mapping_read()

Filemap cleanups:
	[PATCH 09/10] filemap: trivial code cleanups                                  
	[PATCH 10/10] filemap: convert some unsigned long to pgoff_t                  

The diffstat is

 block/ll_rw_blk.c          |    9 ----
 fs/ext3/dir.c              |    2 -
 fs/ext4/dir.c              |    2 -
 fs/splice.c                |    2 -
 include/linux/fs.h         |   14 +++----
 include/linux/mm.h         |    2 -
 include/linux/pagemap.h    |   23 ++++++------
 include/linux/radix-tree.h |    2 +
 lib/radix-tree.c           |   36 +++++++++++++++++++
 mm/filemap.c               |   65 ++++++++++++++++-------------------
 mm/readahead.c             |   58 +++++++++++++++++--------------
 11 files changed, 122 insertions(+), 93 deletions(-)

Regards,
Fengguang Wu
--

[PATCH 01/10] readahead: compacting file_ra_state

[Fengguang Wu]

[-- Attachment #1: short-rasize.patch --]
[-- Type: text/plain, Size: 2010 bytes --]

Use 'unsigned int' instead of 'unsigned long' for readahead sizes.

This helps reduce memory consumption on 64bit CPU when
a lot of files are opened.

CC: Andi Kleen <andi@firstfloor.org>
Signed-off-by: Fengguang Wu <wfg@mail.ustc.edu.cn>
---
 include/linux/fs.h |    8 ++++----
 mm/filemap.c       |    2 +-
 mm/readahead.c     |    2 +-
 3 files changed, 6 insertions(+), 6 deletions(-)

--- linux-2.6.22-rc6-mm1.orig/include/linux/fs.h
+++ linux-2.6.22-rc6-mm1/include/linux/fs.h
@@ -771,12 +771,12 @@ struct fown_struct {
  * Track a single file's readahead state
  */
 struct file_ra_state {
-	pgoff_t start;                  /* where readahead started */
-	unsigned long size;             /* # of readahead pages */
-	unsigned long async_size;       /* do asynchronous readahead when
+	pgoff_t start;			/* where readahead started */
+	unsigned int size;		/* # of readahead pages */
+	unsigned int async_size;	/* do asynchronous readahead when
 					   there are only # of pages ahead */
 
-	unsigned long ra_pages;		/* Maximum readahead window */
+	unsigned int ra_pages;		/* Maximum readahead window */
 	unsigned long mmap_hit;		/* Cache hit stat for mmap accesses */
 	unsigned long mmap_miss;	/* Cache miss stat for mmap accesses */
 	unsigned long prev_index;	/* Cache last read() position */
--- linux-2.6.22-rc6-mm1.orig/mm/filemap.c
+++ linux-2.6.22-rc6-mm1/mm/filemap.c
@@ -840,7 +840,7 @@ static void shrink_readahead_size_eio(st
 	if (count > 5)
 		return;
 	count++;
-	printk(KERN_WARNING "Reducing readahead size to %luK\n",
+	printk(KERN_WARNING "Reducing readahead size to %dK\n",
 		ra->ra_pages << (PAGE_CACHE_SHIFT - 10));
 }
 
--- linux-2.6.22-rc6-mm1.orig/mm/readahead.c
+++ linux-2.6.22-rc6-mm1/mm/readahead.c
@@ -342,7 +342,7 @@ ondemand_readahead(struct address_space 
 		   bool hit_readahead_marker, pgoff_t offset,
 		   unsigned long req_size)
 {
-	unsigned long max;	/* max readahead pages */
+	int max;	/* max readahead pages */
 	int sequential;
 
 	max = ra->ra_pages;

--

[PATCH 02/10] readahead: mmap read-around simplification

[Fengguang Wu]

[-- Attachment #1: remove-mmap-hit.patch --]
[-- Type: text/plain, Size: 1360 bytes --]

Fold file_ra_state.mmap_hit into file_ra_state.mmap_miss
and make it an int.

Signed-off-by: Fengguang Wu <wfg@mail.ustc.edu.cn>
---
 include/linux/fs.h |    3 +--
 mm/filemap.c       |    4 ++--
 2 files changed, 3 insertions(+), 4 deletions(-)

--- linux-2.6.22-rc6-mm1.orig/include/linux/fs.h
+++ linux-2.6.22-rc6-mm1/include/linux/fs.h
@@ -777,8 +777,7 @@ struct file_ra_state {
 					   there are only # of pages ahead */
 
 	unsigned int ra_pages;		/* Maximum readahead window */
-	unsigned long mmap_hit;		/* Cache hit stat for mmap accesses */
-	unsigned long mmap_miss;	/* Cache miss stat for mmap accesses */
+	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 */
 };
--- linux-2.6.22-rc6-mm1.orig/mm/filemap.c
+++ linux-2.6.22-rc6-mm1/mm/filemap.c
@@ -1389,7 +1389,7 @@ retry_find:
 		 * Do we miss much more than hit in this file? If so,
 		 * stop bothering with read-ahead. It will only hurt.
 		 */
-		if (ra->mmap_miss > ra->mmap_hit + MMAP_LOTSAMISS)
+		if (ra->mmap_miss > MMAP_LOTSAMISS)
 			goto no_cached_page;
 
 		/*
@@ -1415,7 +1415,7 @@ retry_find:
 	}
 
 	if (!did_readaround)
-		ra->mmap_hit++;
+		ra->mmap_miss--;
 
 	/*
 	 * We have a locked page in the page cache, now we need to check

--

[PATCH 03/10] readahead: combine file_ra_state.prev_index/prev_offset into prev_pos

[Fengguang Wu]

[-- Attachment #1: merge-start-prev_index.patch --]
[-- Type: text/plain, Size: 4936 bytes --]

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 <peterz@infradead.org>
Signed-off-by: Fengguang Wu <wfg@mail.ustc.edu.cn>
---
 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 int ext4_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 = ext4_bread(NULL, inode, blk, 0, &err);
 		}
 
--- linux-2.6.22-rc6-mm1.orig/fs/splice.c
+++ linux-2.6.22-rc6-mm1/fs/splice.c
@@ -455,7 +455,7 @@ fill_it:
 	 */
 	while (page_nr < nr_pages)
 		page_cache_release(pages[page_nr++]);
-	in->f_ra.prev_index = index;
+	in->f_ra.prev_pos = index << PAGE_CACHE_SHIFT;
 
 	if (spd.nr_pages)
 		return splice_to_pipe(pipe, &spd);

--

Re: [PATCH 03/10] readahead: combine file_ra_state.prev_index/prev_offset into prev_pos

[Andrew Morton]

On Tue, 24 Jul 2007 10:00:12 +0800 Fengguang Wu <wfg@mail.ustc.edu.cn> wrote:

> -	ra->prev_index = page->index;
> +	ra->prev_pos = page->index << PAGE_CACHE_SHIFT;

bug!  The rhs will get truncated befire it gets assigned to
the lhs.  Need to cast page->index to loff_t.

I'll fix this one up.  Please review the other patches for this?


I decided to merge this ahead of that great pile of Nick's patches
(pagecache write deadlocks) and gto a number of easy-to-fix rejects as a
result.  Hopefully it all landed OK.

Re: [PATCH 03/10] readahead: combine file_ra_state.prev_index/prev_offset into prev_pos

[Fengguang Wu]

On Mon, Jul 23, 2007 at 08:52:41PM -0700, Andrew Morton wrote:
> On Tue, 24 Jul 2007 10:00:12 +0800 Fengguang Wu <wfg@mail.ustc.edu.cn> wrote:
> 
> > -	ra->prev_index = page->index;
> > +	ra->prev_pos = page->index << PAGE_CACHE_SHIFT;
> 
> bug!  The rhs will get truncated befire it gets assigned to
> the lhs.  Need to cast page->index to loff_t.
> 
> I'll fix this one up.  Please review the other patches for this?

Thank you. Be sure to update *all* the lines:
        ra->prev_pos = page->index << PAGE_CACHE_SHIFT

Other places should have been taken care of.

Re: [PATCH 03/10] readahead: combine file_ra_state.prev_index/prev_offset into prev_pos

[Andrew Morton]

On Tue, 24 Jul 2007 10:00:12 +0800 Fengguang Wu <wfg@mail.ustc.edu.cn> wrote:

> @@ -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;

It's a bit pointless using an opaque type for prev_offset here, and then
encoding the knowledge that it is implemented as "unsigned long".

It's a minor thing, but perhaps just "<= 1" would make more sense here.

Re: [PATCH 03/10] readahead: combine file_ra_state.prev_index/prev_offset into prev_pos

[Fengguang Wu]

On Mon, Jul 23, 2007 at 08:55:35PM -0700, Andrew Morton wrote:
> On Tue, 24 Jul 2007 10:00:12 +0800 Fengguang Wu <wfg@mail.ustc.edu.cn> wrote:
> 
> > @@ -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;
> 
> It's a bit pointless using an opaque type for prev_offset here, and then
> encoding the knowledge that it is implemented as "unsigned long".
> 
> It's a minor thing, but perhaps just "<= 1" would make more sense here.

Yeah, "<= 1" is OK.  But the expression still requires pgoff_t to be
'unsigned' to work correctly.

So what about "<= 1U"?

Re: [PATCH 03/10] readahead: combine file_ra_state.prev_index/prev_offset into prev_pos

[Andrew Morton]

On Tue, 24 Jul 2007 12:32:15 +0800 Fengguang Wu <wfg@mail.ustc.edu.cn> wrote:

> On Mon, Jul 23, 2007 at 08:55:35PM -0700, Andrew Morton wrote:
> > On Tue, 24 Jul 2007 10:00:12 +0800 Fengguang Wu <wfg@mail.ustc.edu.cn> wrote:
> > 
> > > @@ -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;
> > 
> > It's a bit pointless using an opaque type for prev_offset here, and then
> > encoding the knowledge that it is implemented as "unsigned long".
> > 
> > It's a minor thing, but perhaps just "<= 1" would make more sense here.
> 
> Yeah, "<= 1" is OK.  But the expression still requires pgoff_t to be
> 'unsigned' to work correctly.
> 
> So what about "<= 1U"?

umm, if one really cared one could do

	<expr> == 1 || <expr> == 0

or something.  But whatever - let's leave it as-is.

Re: [PATCH 03/10] readahead: combine file_ra_state.prev_index/prev_offset into prev_pos

[Fengguang Wu]

On Mon, Jul 23, 2007 at 09:53:10PM -0700, Andrew Morton wrote:
> On Tue, 24 Jul 2007 12:32:15 +0800 Fengguang Wu <wfg@mail.ustc.edu.cn> wrote:
> 
> > On Mon, Jul 23, 2007 at 08:55:35PM -0700, Andrew Morton wrote:
> > > On Tue, 24 Jul 2007 10:00:12 +0800 Fengguang Wu <wfg@mail.ustc.edu.cn> wrote:
> > > 
> > > > @@ -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;
> > > 
> > > It's a bit pointless using an opaque type for prev_offset here, and then
> > > encoding the knowledge that it is implemented as "unsigned long".
> > > 
> > > It's a minor thing, but perhaps just "<= 1" would make more sense here.
> > 
> > Yeah, "<= 1" is OK.  But the expression still requires pgoff_t to be
> > 'unsigned' to work correctly.
> > 
> > So what about "<= 1U"?
> 
> umm, if one really cared one could do
> 
> 	<expr> == 1 || <expr> == 0

Yeah, I'd prefer this if we are to change it.

> or something.  But whatever - let's leave it as-is.

Re: [PATCH 03/10] readahead: combine file_ra_state.prev_index/prev_offset into prev_pos

[Fengguang Wu]

On Tue, Jul 24, 2007 at 12:32:15PM +0800, Fengguang Wu wrote:
> On Mon, Jul 23, 2007 at 08:55:35PM -0700, Andrew Morton wrote:
> > On Tue, 24 Jul 2007 10:00:12 +0800 Fengguang Wu <wfg@mail.ustc.edu.cn> wrote:
> > 
> > > @@ -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;
> > 
> > It's a bit pointless using an opaque type for prev_offset here, and then
> > encoding the knowledge that it is implemented as "unsigned long".
> > 
> > It's a minor thing, but perhaps just "<= 1" would make more sense here.
> 
> Yeah, "<= 1" is OK.  But the expression still requires pgoff_t to be
> 'unsigned' to work correctly.
> 
> So what about "<= 1U"?

I wrote a test case and find that if pgoff_t is 'signed long',
"<= 1U" still yields the wrong result. Only "<= 1UL" does the trick :(

[PATCH 04/10] radixtree: introduce radix_tree_scan_hole()

[Fengguang Wu]

[-- Attachment #1: radixtree-introduce-scan-hole-data-functions.patch --]
[-- Type: text/plain, Size: 2552 bytes --]

Introduce radix_tree_scan_hole(root, index, max_scan) to scan radix tree
for the first hole. It will be used in interleaved readahead.

The implementation is dumb and obviously correct.
It can help debug(and document) the possible smart one in future.

Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Signed-off-by: Fengguang Wu <wfg@mail.ustc.edu.cn>
---

 include/linux/radix-tree.h |    2 +
 lib/radix-tree.c           |   36 +++++++++++++++++++++++++++++++++++
 2 files changed, 38 insertions(+)

--- linux-2.6.22-rc6-mm1.orig/include/linux/radix-tree.h
+++ linux-2.6.22-rc6-mm1/include/linux/radix-tree.h
@@ -155,6 +155,8 @@ void *radix_tree_delete(struct radix_tre
 unsigned int
 radix_tree_gang_lookup(struct radix_tree_root *root, void **results,
 			unsigned long first_index, unsigned int max_items);
+unsigned long radix_tree_next_hole(struct radix_tree_root *root,
+				unsigned long index, unsigned long max_scan);
 int radix_tree_preload(gfp_t gfp_mask);
 void radix_tree_init(void);
 void *radix_tree_tag_set(struct radix_tree_root *root,
--- linux-2.6.22-rc6-mm1.orig/lib/radix-tree.c
+++ linux-2.6.22-rc6-mm1/lib/radix-tree.c
@@ -601,6 +601,42 @@ int radix_tree_tag_get(struct radix_tree
 EXPORT_SYMBOL(radix_tree_tag_get);
 #endif
 
+/**
+ *	radix_tree_next_hole    -    find the next hole (not-present entry)
+ *	@root:		tree root
+ *	@index:		index key
+ *	@max_scan:	maximum range to search
+ *
+ *	Search the set [index, min(index+max_scan-1, MAX_INDEX)] for the lowest
+ *	indexed hole.
+ *
+ *	Returns: the index of the hole if found, otherwise returns an index
+ *	outside of the set specified (in which case 'return - index >= max_scan'
+ *	will be true).
+ *
+ *	radix_tree_next_hole may be called under rcu_read_lock. However, like
+ *	radix_tree_gang_lookup, this will not atomically search a snapshot of the
+ *	tree at a single point in time. For example, if a hole is created at index
+ *	5, then subsequently a hole is created at index 10, radix_tree_next_hole
+ *	covering both indexes may return 10 if called under rcu_read_lock.
+ */
+unsigned long radix_tree_next_hole(struct radix_tree_root *root,
+				unsigned long index, unsigned long max_scan)
+{
+	unsigned long i;
+
+	for (i = 0; i < max_scan; i++) {
+		if (!radix_tree_lookup(root, index))
+			break;
+		index++;
+		if (index == 0)
+			break;
+	}
+
+	return index;
+}
+EXPORT_SYMBOL(radix_tree_next_hole);
+
 static unsigned int
 __lookup(struct radix_tree_node *slot, void **results, unsigned long index,
 	unsigned int max_items, unsigned long *next_index)

--

[PATCH 05/10] readahead: basic support of interleaved reads

[Fengguang Wu]

[-- Attachment #1: readahead-interleaved-reads.patch --]
[-- Type: text/plain, Size: 3282 bytes --]

This is a simplified version of the pagecache context based readahead.
It handles the case of multiple threads reading on the same fd and invalidating
each others' readahead state. It does the trick by scanning the pagecache and
recovering the current read stream's readahead status.

The algorithm works in a opportunistic way, in that it do not try to detect
interleaved reads _actively_, which requires a probe into the page cache(which
means a little more overheads for random reads). It only tries to handle a
previously started sequential readahead whose state was overwritten by
another concurrent stream, and it can do this job pretty well.

Negative and positive examples(or what you can expect from it):

1) it cannot detect and serve perfect request-by-request interleaved reads
   right:
	time	stream 1  stream 2
	0 	1         
	1 	          1001
	2 	2
	3 	          1002
	4 	3
	5 	          1003
	6 	4
	7 	          1004
	8 	5
	9	          1005
Here no single readahead will be carried out.

2) However, if it's two concurrent reads by two threads, the chance of the
   initial sequential readahead be started is huge. Once the first sequential
   readahead is started for a stream, this patch will ensure that the readahead
   window continues to rampup and won't be disturbed by other streams.

	time	stream 1  stream 2
	0 	1         
	1 	2
	2 	          1001
	3 	3
	4 	          1002
	5 	          1003
	6 	4
	7 	5
	8 	          1004
	9 	6
	10	          1005
	11	7
	12	          1006
	13	          1007
Here steam 1 will start a readahead at page 2, and stream 2 will start its
first readahead at page 1003. From then on the two streams will be served right.

Cc: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Fengguang Wu <wfg@mail.ustc.edu.cn>
---
 mm/readahead.c |   33 +++++++++++++++++++++++----------
 1 file changed, 23 insertions(+), 10 deletions(-)

--- linux-2.6.22-rc6-mm1.orig/mm/readahead.c
+++ linux-2.6.22-rc6-mm1/mm/readahead.c
@@ -371,6 +371,29 @@ ondemand_readahead(struct address_space 
 	}
 
 	/*
+	 * Hit a marked page without valid readahead state.
+	 * E.g. interleaved reads.
+	 * Query the pagecache for async_size, which normally equals to
+	 * readahead size. Ramp it up and use it as the new readahead size.
+	 */
+	if (hit_readahead_marker) {
+		pgoff_t start;
+
+		read_lock_irq(&mapping->tree_lock);
+		start = radix_tree_next_hole(&mapping->page_tree, offset, max+1);
+		read_unlock_irq(&mapping->tree_lock);
+
+		if (!start || start - offset > max)
+			return 0;
+
+		ra->start = start;
+		ra->size = start - offset;	/* old async_size */
+		ra->size = get_next_ra_size(ra, max);
+		ra->async_size = ra->size;
+		goto readit;
+	}
+
+	/*
 	 * It may be one of
 	 * 	- first read on start of file
 	 * 	- sequential cache miss
@@ -381,16 +404,6 @@ ondemand_readahead(struct address_space 
 	ra->size = get_init_ra_size(req_size, max);
 	ra->async_size = ra->size > req_size ? ra->size - req_size : ra->size;
 
-	/*
-	 * Hit on a marked page without valid readahead state.
-	 * E.g. interleaved reads.
-	 * Not knowing its readahead pos/size, bet on the minimal possible one.
-	 */
-	if (hit_readahead_marker) {
-		ra->start++;
-		ra->size = get_next_ra_size(ra, max);
-	}
-
 readit:
 	return ra_submit(ra, mapping, filp);
 }

--

[PATCH 06/10] readahead: remove the local copy of ra in do_generic_mapping_read()

[Fengguang Wu]

[-- Attachment #1: remove-duplicate-ra.patch --]
[-- Type: text/plain, Size: 2542 bytes --]

The local copy of ra in do_generic_mapping_read() can now go away.

It predates readanead(req_size).  In a time when the readahead code was called
on *every* single page. Hence a local has to be made to reduce the chance of
the readahead state being overwritten by a concurrent reader. More details in:
Linux: Random File I/O Regressions In 2.6 <http://kerneltrap.org/node/3039>

Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Signed-off-by: Fengguang Wu <wfg@mail.ustc.edu.cn>
---
 mm/filemap.c |   20 +++++++++-----------
 1 file changed, 9 insertions(+), 11 deletions(-)

--- linux-2.6.22-rc6-mm1.orig/mm/filemap.c
+++ linux-2.6.22-rc6-mm1/mm/filemap.c
@@ -863,7 +863,7 @@ static void shrink_readahead_size_eio(st
  * It may be NULL.
  */
 void do_generic_mapping_read(struct address_space *mapping,
-			     struct file_ra_state *_ra,
+			     struct file_ra_state *ra,
 			     struct file *filp,
 			     loff_t *ppos,
 			     read_descriptor_t *desc,
@@ -877,12 +877,11 @@ void do_generic_mapping_read(struct addr
 	unsigned long prev_index;
 	unsigned int prev_offset;
 	int error;
-	struct file_ra_state ra = *_ra;
 
 	index = *ppos >> PAGE_CACHE_SHIFT;
 	next_index = index;
-	prev_index = ra.prev_pos >> PAGE_CACHE_SHIFT;
-	prev_offset = ra.prev_pos & (PAGE_CACHE_SIZE-1);
+	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;
 
@@ -897,7 +896,7 @@ find_page:
 		page = find_get_page(mapping, index);
 		if (!page) {
 			page_cache_sync_readahead(mapping,
-					&ra, filp,
+					ra, filp,
 					index, last_index - index);
 			page = find_get_page(mapping, index);
 			if (unlikely(page == NULL))
@@ -905,7 +904,7 @@ find_page:
 		}
 		if (PageReadahead(page)) {
 			page_cache_async_readahead(mapping,
-					&ra, filp, page,
+					ra, filp, page,
 					index, last_index - index);
 		}
 		if (!PageUptodate(page))
@@ -1016,7 +1015,7 @@ readpage:
 				}
 				unlock_page(page);
 				error = -EIO;
-				shrink_readahead_size_eio(filp, &ra);
+				shrink_readahead_size_eio(filp, ra);
 				goto readpage_error;
 			}
 			unlock_page(page);
@@ -1053,10 +1052,9 @@ no_cached_page:
 	}
 
 out:
-	*_ra = ra;
-	_ra->prev_pos = prev_index;
-	_ra->prev_pos <<= PAGE_CACHE_SHIFT;
-	_ra->prev_pos |= prev_offset;
+	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)

--

[PATCH 07/10] readahead: remove several readahead macros

[Fengguang Wu]

[-- Attachment #1: readahead-macros-cleanup.patch --]
[-- Type: text/plain, Size: 1523 bytes --]

Remove VM_MAX_CACHE_HIT, MAX_RA_PAGES and MIN_RA_PAGES.

Signed-off-by: Fengguang Wu <wfg@mail.ustc.edu.cn>
---
 include/linux/mm.h |    2 --
 mm/readahead.c     |   10 +---------
 2 files changed, 1 insertion(+), 11 deletions(-)

--- linux-2.6.22-rc6-mm1.orig/include/linux/mm.h
+++ linux-2.6.22-rc6-mm1/include/linux/mm.h
@@ -1148,8 +1148,6 @@ int write_one_page(struct page *page, in
 /* readahead.c */
 #define VM_MAX_READAHEAD	128	/* kbytes */
 #define VM_MIN_READAHEAD	16	/* kbytes (includes current page) */
-#define VM_MAX_CACHE_HIT    	256	/* max pages in a row in cache before
-					 * turning readahead off */
 
 int do_page_cache_readahead(struct address_space *mapping, struct file *filp,
 			pgoff_t offset, unsigned long nr_to_read);
--- linux-2.6.22-rc6-mm1.orig/mm/readahead.c
+++ linux-2.6.22-rc6-mm1/mm/readahead.c
@@ -21,16 +21,8 @@ void default_unplug_io_fn(struct backing
 }
 EXPORT_SYMBOL(default_unplug_io_fn);
 
-/*
- * Convienent macros for min/max read-ahead pages.
- * Note that MAX_RA_PAGES is rounded down, while MIN_RA_PAGES is rounded up.
- * The latter is necessary for systems with large page size(i.e. 64k).
- */
-#define MAX_RA_PAGES	(VM_MAX_READAHEAD*1024 / PAGE_CACHE_SIZE)
-#define MIN_RA_PAGES	DIV_ROUND_UP(VM_MIN_READAHEAD*1024, PAGE_CACHE_SIZE)
-
 struct backing_dev_info default_backing_dev_info = {
-	.ra_pages	= MAX_RA_PAGES,
+	.ra_pages	= VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE,
 	.state		= 0,
 	.capabilities	= BDI_CAP_MAP_COPY,
 	.unplug_io_fn	= default_unplug_io_fn,

--

[PATCH 08/10] readahead: remove the limit max_sectors_kb imposed on max_readahead_kb

[Fengguang Wu]

[-- Attachment #1: remove-readahead-size-limit.patch --]
[-- Type: text/plain, Size: 1300 bytes --]

Remove the size limit max_sectors_kb imposed on max_readahead_kb.

The size restriction is unreasonable. Especially when max_sectors_kb cannot
grow larger than max_hw_sectors_kb, which can be rather small for some disk
drives.

Cc: Jens Axboe <jens.axboe@oracle.com>
Signed-off-by: Fengguang Wu <wfg@mail.ustc.edu.cn>
Acked-by: Jens Axboe <jens.axboe@oracle.com>
---
 block/ll_rw_blk.c |    9 ---------
 1 file changed, 9 deletions(-)

--- linux-2.6.22-rc6-mm1.orig/block/ll_rw_blk.c
+++ linux-2.6.22-rc6-mm1/block/ll_rw_blk.c
@@ -3945,7 +3945,6 @@ queue_max_sectors_store(struct request_q
 			max_hw_sectors_kb = q->max_hw_sectors >> 1,
 			page_kb = 1 << (PAGE_CACHE_SHIFT - 10);
 	ssize_t ret = queue_var_store(&max_sectors_kb, page, count);
-	int ra_kb;
 
 	if (max_sectors_kb > max_hw_sectors_kb || max_sectors_kb < page_kb)
 		return -EINVAL;
@@ -3954,14 +3953,6 @@ queue_max_sectors_store(struct request_q
 	 * values synchronously:
 	 */
 	spin_lock_irq(q->queue_lock);
-	/*
-	 * Trim readahead window as well, if necessary:
-	 */
-	ra_kb = q->backing_dev_info.ra_pages << (PAGE_CACHE_SHIFT - 10);
-	if (ra_kb > max_sectors_kb)
-		q->backing_dev_info.ra_pages =
-				max_sectors_kb >> (PAGE_CACHE_SHIFT - 10);
-
 	q->max_sectors = max_sectors_kb << 1;
 	spin_unlock_irq(q->queue_lock);
 

--

[PATCH 09/10] filemap: trivial code cleanups

[Fengguang Wu]

[-- Attachment #1: cleanup-filemap.patch --]
[-- Type: text/plain, Size: 1453 bytes --]

- remove unused local next_index in do_generic_mapping_read()
- wrap a long line
- remove a redudant page_cache_read() declaration

Signed-off-by: Fengguang Wu <wfg@mail.ustc.edu.cn>
---
 mm/filemap.c |    6 ++----
 1 file changed, 2 insertions(+), 4 deletions(-)

--- linux-2.6.22-rc6-mm1.orig/mm/filemap.c
+++ linux-2.6.22-rc6-mm1/mm/filemap.c
@@ -873,13 +873,11 @@ void do_generic_mapping_read(struct addr
 	unsigned long index;
 	unsigned long offset;
 	unsigned long last_index;
-	unsigned long next_index;
 	unsigned long prev_index;
 	unsigned int prev_offset;
 	int error;
 
 	index = *ppos >> PAGE_CACHE_SHIFT;
-	next_index = index;
 	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;
@@ -1214,7 +1212,8 @@ out:
 }
 EXPORT_SYMBOL(generic_file_aio_read);
 
-int file_send_actor(read_descriptor_t * desc, struct page *page, unsigned long offset, unsigned long size)
+int file_send_actor(read_descriptor_t * desc, struct page *page,
+			unsigned long offset, unsigned long size)
 {
 	ssize_t written;
 	unsigned long count = desc->count;
@@ -1287,7 +1286,6 @@ asmlinkage ssize_t sys_readahead(int fd,
 }
 
 #ifdef CONFIG_MMU
-static int FASTCALL(page_cache_read(struct file * file, unsigned long offset));
 /**
  * page_cache_read - adds requested page to the page cache if not already there
  * @file:	file to read

--

[PATCH 10/10] filemap: convert some unsigned long to pgoff_t

[Fengguang Wu]

[-- Attachment #1: pgoff_t.patch --]
[-- Type: text/plain, Size: 7072 bytes --]

Convert some 'unsigned long' to pgoff_t.

Signed-off-by: Fengguang Wu <wfg@mail.ustc.edu.cn>
---
 include/linux/pagemap.h |   23 ++++++++++++-----------
 mm/filemap.c            |   32 ++++++++++++++++----------------
 2 files changed, 28 insertions(+), 27 deletions(-)

--- linux-2.6.22-rc6-mm1.orig/include/linux/pagemap.h
+++ linux-2.6.22-rc6-mm1/include/linux/pagemap.h
@@ -83,11 +83,11 @@ static inline struct page *page_cache_al
 typedef int filler_t(void *, struct page *);
 
 extern struct page * find_get_page(struct address_space *mapping,
-				unsigned long index);
+				pgoff_t index);
 extern struct page * find_lock_page(struct address_space *mapping,
-				unsigned long index);
+				pgoff_t index);
 extern struct page * find_or_create_page(struct address_space *mapping,
-				unsigned long index, gfp_t gfp_mask);
+				pgoff_t index, gfp_t gfp_mask);
 unsigned find_get_pages(struct address_space *mapping, pgoff_t start,
 			unsigned int nr_pages, struct page **pages);
 unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t start,
@@ -100,41 +100,42 @@ struct page *__grab_cache_page(struct ad
 /*
  * Returns locked page at given index in given cache, creating it if needed.
  */
-static inline struct page *grab_cache_page(struct address_space *mapping, unsigned long index)
+static inline struct page *grab_cache_page(struct address_space *mapping,
+								pgoff_t index)
 {
 	return find_or_create_page(mapping, index, mapping_gfp_mask(mapping));
 }
 
 extern struct page * grab_cache_page_nowait(struct address_space *mapping,
-				unsigned long index);
+				pgoff_t index);
 extern struct page * read_cache_page_async(struct address_space *mapping,
-				unsigned long index, filler_t *filler,
+				pgoff_t index, filler_t *filler,
 				void *data);
 extern struct page * read_cache_page(struct address_space *mapping,
-				unsigned long index, filler_t *filler,
+				pgoff_t index, filler_t *filler,
 				void *data);
 extern int read_cache_pages(struct address_space *mapping,
 		struct list_head *pages, filler_t *filler, void *data);
 
 static inline struct page *read_mapping_page_async(
 						struct address_space *mapping,
-					     unsigned long index, void *data)
+						     pgoff_t index, void *data)
 {
 	filler_t *filler = (filler_t *)mapping->a_ops->readpage;
 	return read_cache_page_async(mapping, index, filler, data);
 }
 
 static inline struct page *read_mapping_page(struct address_space *mapping,
-					     unsigned long index, void *data)
+					     pgoff_t index, void *data)
 {
 	filler_t *filler = (filler_t *)mapping->a_ops->readpage;
 	return read_cache_page(mapping, index, filler, data);
 }
 
 int add_to_page_cache(struct page *page, struct address_space *mapping,
-				unsigned long index, gfp_t gfp_mask);
+				pgoff_t index, gfp_t gfp_mask);
 int add_to_page_cache_lru(struct page *page, struct address_space *mapping,
-				unsigned long index, gfp_t gfp_mask);
+				pgoff_t index, gfp_t gfp_mask);
 extern void remove_from_page_cache(struct page *page);
 extern void __remove_from_page_cache(struct page *page);
 
--- linux-2.6.22-rc6-mm1.orig/mm/filemap.c
+++ linux-2.6.22-rc6-mm1/mm/filemap.c
@@ -594,7 +594,7 @@ void fastcall __lock_page_nosync(struct 
  * Is there a pagecache struct page at the given (mapping, offset) tuple?
  * If yes, increment its refcount and return it; if no, return NULL.
  */
-struct page * find_get_page(struct address_space *mapping, unsigned long offset)
+struct page * find_get_page(struct address_space *mapping, pgoff_t offset)
 {
 	struct page *page;
 
@@ -618,7 +618,7 @@ EXPORT_SYMBOL(find_get_page);
  * Returns zero if the page was not present. find_lock_page() may sleep.
  */
 struct page *find_lock_page(struct address_space *mapping,
-				unsigned long offset)
+				pgoff_t offset)
 {
 	struct page *page;
 
@@ -664,7 +664,7 @@ EXPORT_SYMBOL(find_lock_page);
  * memory exhaustion.
  */
 struct page *find_or_create_page(struct address_space *mapping,
-		unsigned long index, gfp_t gfp_mask)
+		pgoff_t index, gfp_t gfp_mask)
 {
 	struct page *page;
 	int err;
@@ -794,7 +794,7 @@ EXPORT_SYMBOL(find_get_pages_tag);
  * and deadlock against the caller's locked page.
  */
 struct page *
-grab_cache_page_nowait(struct address_space *mapping, unsigned long index)
+grab_cache_page_nowait(struct address_space *mapping, pgoff_t index)
 {
 	struct page *page = find_get_page(mapping, index);
 
@@ -870,10 +870,10 @@ void do_generic_mapping_read(struct addr
 			     read_actor_t actor)
 {
 	struct inode *inode = mapping->host;
-	unsigned long index;
-	unsigned long offset;
-	unsigned long last_index;
-	unsigned long prev_index;
+	pgoff_t index;
+	pgoff_t last_index;
+	pgoff_t prev_index;
+	unsigned long offset;      /* offset into pagecache page */
 	unsigned int prev_offset;
 	int error;
 
@@ -885,7 +885,7 @@ void do_generic_mapping_read(struct addr
 
 	for (;;) {
 		struct page *page;
-		unsigned long end_index;
+		pgoff_t end_index;
 		loff_t isize;
 		unsigned long nr, ret;
 
@@ -1255,7 +1255,7 @@ EXPORT_SYMBOL(generic_file_sendfile);
 
 static ssize_t
 do_readahead(struct address_space *mapping, struct file *filp,
-	     unsigned long index, unsigned long nr)
+	     pgoff_t index, unsigned long nr)
 {
 	if (!mapping || !mapping->a_ops || !mapping->a_ops->readpage)
 		return -EINVAL;
@@ -1275,8 +1275,8 @@ asmlinkage ssize_t sys_readahead(int fd,
 	if (file) {
 		if (file->f_mode & FMODE_READ) {
 			struct address_space *mapping = file->f_mapping;
-			unsigned long start = offset >> PAGE_CACHE_SHIFT;
-			unsigned long end = (offset + count - 1) >> PAGE_CACHE_SHIFT;
+			pgoff_t start = offset >> PAGE_CACHE_SHIFT;
+			pgoff_t end = (offset + count - 1) >> PAGE_CACHE_SHIFT;
 			unsigned long len = end - start + 1;
 			ret = do_readahead(mapping, file, start, len);
 		}
@@ -1294,7 +1294,7 @@ asmlinkage ssize_t sys_readahead(int fd,
  * This adds the requested page to the page cache if it isn't already there,
  * and schedules an I/O to read in its contents from disk.
  */
-static int fastcall page_cache_read(struct file * file, unsigned long offset)
+static int fastcall page_cache_read(struct file * file, pgoff_t offset)
 {
 	struct address_space *mapping = file->f_mapping;
 	struct page *page; 
@@ -1540,7 +1540,7 @@ EXPORT_SYMBOL(generic_file_mmap);
 EXPORT_SYMBOL(generic_file_readonly_mmap);
 
 static struct page *__read_cache_page(struct address_space *mapping,
-				unsigned long index,
+				pgoff_t index,
 				int (*filler)(void *,struct page*),
 				void *data)
 {
@@ -1574,7 +1574,7 @@ repeat:
  * after submitting it to the filler.
  */
 struct page *read_cache_page_async(struct address_space *mapping,
-				unsigned long index,
+				pgoff_t index,
 				int (*filler)(void *,struct page*),
 				void *data)
 {
@@ -1623,7 +1623,7 @@ EXPORT_SYMBOL(read_cache_page_async);
  * If the page does not get brought uptodate, return -EIO.
  */
 struct page *read_cache_page(struct address_space *mapping,
-				unsigned long index,
+				pgoff_t index,
 				int (*filler)(void *,struct page*),
 				void *data)
 {

--