From: Suparna Bhattacharya <suparna@in.ibm.com>
DESC
aio O_DIRECT no readahead
EDESC
From: Daniel McNeil <daniel@osdl.org>
More testing on AIO with O_DIRECT and /dev/raw/. Doing AIO reads was
using a lot more cpu time than using dd on the raw partition even with
the io_queue_wait patch. Found out that aio is doing readahead even
for O_DIRECT. Here's a patch that fixes it.
DESC
Unified page range readahead for aio and regular reads
EDESC
From: Suparna Bhattacharya <suparna@in.ibm.com>
The open coded readahead logic which was added in aio_pread is best avoided
if possible. Duplicating similar checks across sync and aio paths (e.g.
checking for O_DIRECT) and the divergence of logic between these paths
isn't good from a long term maintainability standpoint.
Secondly, this logic really belongs in the generic fops methods for
aio_read rather than in the high level aio handlers; it should be possible
for a filesystem to override the logic with its own if suitable.
So, this patch moves the readahead out of aio_pread, and instead modifies
do_generic_mapping_read to readahead _all_ the pages in the range requested
upfront before it starts waiting for any of the pages to become uptodate.
This leads to sane readahead behaviour for the kind of i/o patterns
generated by streaming aio reads. It also takes care not to repeatedly
issue readaheads for subsequent AIO retries for the same request.
fs/aio.c | 1 +
include/linux/aio.h | 3 +++
mm/filemap.c | 18 +++++++++++++-----
3 files changed, 17 insertions(+), 5 deletions(-)
diff -puN fs/aio.c~aio-12-readahead fs/aio.c
--- 25/fs/aio.c~aio-12-readahead 2003-10-26 21:53:50.000000000 -0800
+++ 25-akpm/fs/aio.c 2003-10-26 21:53:50.000000000 -0800
@@ -28,6 +28,7 @@
#include <linux/highmem.h>
#include <linux/workqueue.h>
#include <linux/writeback.h>
+#include <linux/pagemap.h>
#include <asm/kmap_types.h>
#include <asm/uaccess.h>
diff -puN mm/filemap.c~aio-12-readahead mm/filemap.c
--- 25/mm/filemap.c~aio-12-readahead 2003-10-26 21:53:50.000000000 -0800
+++ 25-akpm/mm/filemap.c 2003-10-26 21:53:50.000000000 -0800
@@ -664,7 +664,8 @@ void do_generic_mapping_read(struct addr
read_actor_t actor)
{
struct inode *inode = mapping->host;
- unsigned long index, offset, last;
+ unsigned long index, offset, last, end_index;
+ loff_t isize = i_size_read(inode);
struct page *cached_page;
int error;
@@ -672,6 +673,15 @@ void do_generic_mapping_read(struct addr
index = *ppos >> PAGE_CACHE_SHIFT;
offset = *ppos & ~PAGE_CACHE_MASK;
last = (*ppos + desc->count) >> PAGE_CACHE_SHIFT;
+ end_index = isize >> PAGE_CACHE_SHIFT;
+ if (last > end_index)
+ last = end_index;
+
+ /* Don't repeat the readahead if we are executing aio retries */
+ if (in_aio()) {
+ if (is_retried_kiocb(io_wait_to_kiocb(current->io_wait)))
+ goto done_readahead;
+ }
/*
* Let the readahead logic know upfront about all
@@ -681,13 +691,11 @@ void do_generic_mapping_read(struct addr
page_cache_readahead(mapping, ra, filp, index);
index = *ppos >> PAGE_CACHE_SHIFT;
+done_readahead:
for (;;) {
struct page *page;
- unsigned long end_index, nr, ret;
- loff_t isize = i_size_read(inode);
+ unsigned long nr, ret;
- end_index = isize >> PAGE_CACHE_SHIFT;
-
if (index > end_index)
break;
nr = PAGE_CACHE_SIZE;
diff -puN include/linux/aio.h~aio-12-readahead include/linux/aio.h
--- 25/include/linux/aio.h~aio-12-readahead 2003-10-26 21:53:50.000000000 -0800
+++ 25-akpm/include/linux/aio.h 2003-10-26 21:53:50.000000000 -0800
@@ -184,6 +184,9 @@ int FASTCALL(io_submit_one(struct kioctx
dump_stack(); \
}
+#define io_wait_to_kiocb(wait) container_of(wait, struct kiocb, ki_wait)
+#define is_retried_kiocb(iocb) ((iocb)->ki_retried > 1)
+
#include <linux/aio_abi.h>
static inline struct kiocb *list_kiocb(struct list_head *h)
_