Variable Order Page Cache: Readahead fixups
Readahead is now dependent on the page size. For larger page sizes
we want less readahead.
Add a parameter to max_sane_readahead specifying the page order
and update the code in mm/readahead.c to be aware of variant
page sizes.
[WARNING untested likely does not compile.....]
---
include/linux/mm.h | 2 +-
mm/fadvise.c | 5 +++--
mm/filemap.c | 5 +++--
mm/madvise.c | 4 +++-
mm/readahead.c | 12 ++++++------
5 files changed, 16 insertions(+), 12 deletions(-)
Index: linux-2.6.21-rc7/include/linux/mm.h
===================================================================
--- linux-2.6.21-rc7.orig/include/linux/mm.h 2007-04-19 21:24:12.000000000
-0700
+++ linux-2.6.21-rc7/include/linux/mm.h 2007-04-19 21:26:16.000000000 -0700
@@ -1084,7 +1084,7 @@ unsigned long page_cache_readahead(struc
unsigned long size);
void handle_ra_miss(struct address_space *mapping,
struct file_ra_state *ra, pgoff_t offset);
-unsigned long max_sane_readahead(unsigned long nr);
+unsigned long max_sane_readahead(unsigned long nr, int order);
/* Do stack extension */
extern int expand_stack(struct vm_area_struct *vma, unsigned long address);
Index: linux-2.6.21-rc7/mm/fadvise.c
===================================================================
--- linux-2.6.21-rc7.orig/mm/fadvise.c 2007-04-19 21:24:12.000000000 -0700
+++ linux-2.6.21-rc7/mm/fadvise.c 2007-04-19 21:26:16.000000000 -0700
@@ -86,10 +86,11 @@ asmlinkage long sys_fadvise64_64(int fd,
nrpages = end_index - start_index + 1;
if (!nrpages)
nrpages = ~0UL;
-
+
ret = force_page_cache_readahead(mapping, file,
start_index,
- max_sane_readahead(nrpages));
+ max_sane_readahead(nrpages,
+ mapping->order));
if (ret > 0)
ret = 0;
break;
Index: linux-2.6.21-rc7/mm/filemap.c
===================================================================
--- linux-2.6.21-rc7.orig/mm/filemap.c 2007-04-19 21:24:12.000000000 -0700
+++ linux-2.6.21-rc7/mm/filemap.c 2007-04-19 21:26:16.000000000 -0700
@@ -1246,7 +1246,7 @@ do_readahead(struct address_space *mappi
return -EINVAL;
force_page_cache_readahead(mapping, filp, index,
- max_sane_readahead(nr));
+ max_sane_readahead(nr, mapping->order));
return 0;
}
@@ -1381,7 +1381,8 @@ retry_find:
count_vm_event(PGMAJFAULT);
}
did_readaround = 1;
- ra_pages = max_sane_readahead(file->f_ra.ra_pages);
+ ra_pages = max_sane_readahead(file->f_ra.ra_pages,
+ mapping->order);
if (ra_pages) {
pgoff_t start = 0;
Index: linux-2.6.21-rc7/mm/madvise.c
===================================================================
--- linux-2.6.21-rc7.orig/mm/madvise.c 2007-04-19 21:24:12.000000000 -0700
+++ linux-2.6.21-rc7/mm/madvise.c 2007-04-19 21:26:16.000000000 -0700
@@ -105,7 +105,9 @@ static long madvise_willneed(struct vm_a
end = ((end - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
force_page_cache_readahead(file->f_mapping,
- file, start, max_sane_readahead(end - start));
+ file, start,
+ max_sane_readahead(end - start,
+ file->f_mapping->order));
return 0;
}
Index: linux-2.6.21-rc7/mm/readahead.c
===================================================================
--- linux-2.6.21-rc7.orig/mm/readahead.c 2007-04-19 21:24:12.000000000
-0700
+++ linux-2.6.21-rc7/mm/readahead.c 2007-04-19 21:26:16.000000000 -0700
@@ -152,7 +152,7 @@ int read_cache_pages(struct address_spac
put_pages_list(pages);
break;
}
- task_io_account_read(PAGE_CACHE_SIZE);
+ task_io_account_read(page_cache_size(mapping));
}
pagevec_lru_add(&lru_pvec);
return ret;
@@ -276,7 +276,7 @@ __do_page_cache_readahead(struct address
if (isize == 0)
goto out;
- end_index = ((isize - 1) >> PAGE_CACHE_SHIFT);
+ end_index = ((isize - 1) >> page_cache_shift(mapping));
/*
* Preallocate as many pages as we will need.
@@ -330,7 +330,7 @@ int force_page_cache_readahead(struct ad
while (nr_to_read) {
int err;
- unsigned long this_chunk = (2 * 1024 * 1024) / PAGE_CACHE_SIZE;
+ unsigned long this_chunk = (2 * 1024 * 1024) /
page_cache_size(mapping);
if (this_chunk > nr_to_read)
this_chunk = nr_to_read;
@@ -570,11 +570,11 @@ void handle_ra_miss(struct address_space
}
/*
- * Given a desired number of PAGE_CACHE_SIZE readahead pages, return a
+ * Given a desired number of page order readahead pages, return a
* sensible upper limit.
*/
-unsigned long max_sane_readahead(unsigned long nr)
+unsigned long max_sane_readahead(unsigned long nr, int order)
{
return min(nr, (node_page_state(numa_node_id(), NR_INACTIVE)
- + node_page_state(numa_node_id(), NR_FREE_PAGES)) / 2);
+ + node_page_state(numa_node_id(), NR_FREE_PAGES)) / 2 >> order);
}
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [EMAIL PROTECTED]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
