On Wed, Oct 07, 2009 at 11:50:58PM +0800, Nikita Danilov wrote:
> 2009/10/7 Wu Fengguang <fengguang.wu@xxxxxxxxx>:
>
> [...]
>
> > + */
> > + if (current_is_kswapd() &&
> > + bdi_cap_writeback_dirty(mapping->backing_dev_info) &&
> > + !mapping->a_ops->writepages) {
> > + wbc.range_start = (page->index + 1) << PAGE_CACHE_SHIFT;
> > + wbc.nr_to_write = LUMPY_PAGEOUT_PAGES - 1;
> > + generic_writepages(mapping, &wbc);
> > + iput(inode);
> > + }
> > +
> > + /*
>
> One potential problem with this is that generic_writepages() waits on
> page locks and this can stall kswapd (always bad). This can be worked
> around by replacing lock_page() with trylock_page() conditionally on
> wbc->for_reclaim (or wbc->nonblocking?), but then, this almost look
> like a separate function would be better.
IMHO trylock_page() is not necessary. Locked pages are rare in normal
states. kswapd already do lock_page() for all pages it try to examine
state for reclaim. So it makes sense for lumpy pageout to follow the
(simple) convention.
> On a good side, it seems I was wrong and pageout calls iput() already:
> shrink_slab()->prune_icache()->iput().
Not totally wrong ;) iput() will be called if __GFP_FS is on. However
pageout may be called on either __GFP_FS or (__GFP_IO && PageSwapCache).
So I updated the patch to do lumpy pageout for __GFP_FS. In long term,
it would be good to remove AOP_WRITEPAGE_ACTIVATE and ->writepage()
totally, and to support shmem as well :)
Thanks,
Fengguang
---
vmscan: lumpy pageout
When pageout a dirty page, try to piggy back more consecutive dirty
pages (up to 512KB) to improve IO efficiency.
Only ext3/reiserfs which don't have its own aops->writepages are
supported in this initial version.
CC: Hugh Dickins <hugh.dickins@xxxxxxxxxxxxx>
CC: Dave Chinner <david@xxxxxxxxxxxxx>
CC: Nikita Danilov <danilov@xxxxxxxxx>
Signed-off-by: Wu Fengguang <fengguang.wu@xxxxxxxxx>
---
mm/page-writeback.c | 12 ++++++++++++
mm/vmscan.c | 23 ++++++++++++++++++++++-
2 files changed, 34 insertions(+), 1 deletion(-)
--- linux.orig/mm/vmscan.c 2009-10-08 07:35:06.000000000 +0800
+++ linux/mm/vmscan.c 2009-10-08 10:20:51.000000000 +0800
@@ -344,11 +344,14 @@ typedef enum {
PAGE_CLEAN,
} pageout_t;
+#define LUMPY_PAGEOUT_PAGES (512 * 1024 / PAGE_CACHE_SIZE)
+
/*
* pageout is called by shrink_page_list() for each dirty page.
* Calls ->writepage().
*/
static pageout_t pageout(struct page *page, struct address_space *mapping,
+ struct scan_control *sc,
enum pageout_io sync_writeback)
{
/*
@@ -398,6 +401,10 @@ static pageout_t pageout(struct page *pa
.nonblocking = 1,
.for_reclaim = 1,
};
+ struct inode *inode = NULL;
+
+ if (sc->gfp_mask & __GFP_FS)
+ inode = igrab(mapping->host);
SetPageReclaim(page);
res = mapping->a_ops->writepage(page, &wbc);
@@ -405,10 +412,24 @@ static pageout_t pageout(struct page *pa
handle_write_error(mapping, page, res);
if (res == AOP_WRITEPAGE_ACTIVATE) {
ClearPageReclaim(page);
+ iput(inode);
return PAGE_ACTIVATE;
}
/*
+ * only write_cache_pages() supports for_reclaim for now
+ * ignore shmem for now, thanks to Nikita.
+ */
+ if (current_is_kswapd() &&
+ bdi_cap_writeback_dirty(mapping->backing_dev_info) &&
+ !mapping->a_ops->writepages) {
+ wbc.range_start = (page->index + 1) << PAGE_CACHE_SHIFT;
+ wbc.nr_to_write = LUMPY_PAGEOUT_PAGES - 1;
+ generic_writepages(mapping, &wbc);
+ iput(inode);
+ }
+
+ /*
* Wait on writeback if requested to. This happens when
* direct reclaiming a large contiguous area and the
* first attempt to free a range of pages fails.
@@ -684,7 +705,7 @@ static unsigned long shrink_page_list(st
goto keep_locked;
/* Page is dirty, try to write it out here */
- switch (pageout(page, mapping, sync_writeback)) {
+ switch (pageout(page, mapping, sc, sync_writeback)) {
case PAGE_KEEP:
goto keep_locked;
case PAGE_ACTIVATE:
--- linux.orig/mm/page-writeback.c 2009-10-08 07:38:57.000000000 +0800
+++ linux/mm/page-writeback.c 2009-10-08 10:06:33.000000000 +0800
@@ -805,6 +805,11 @@ int write_cache_pages(struct address_spa
break;
}
+ if (wbc->for_reclaim && done_index != page->index) {
+ done = 1;
+ break;
+ }
+
if (nr_to_write != wbc->nr_to_write &&
done_index + WB_SEGMENT_DIST < page->index &&
--wbc->nr_segments <= 0) {
@@ -846,6 +851,13 @@ continue_unlock:
if (!clear_page_dirty_for_io(page))
goto continue_unlock;
+ /*
+ * active and unevictable pages will be checked at
+ * rotate time
+ */
+ if (wbc->for_reclaim)
+ SetPageReclaim(page);
+
ret = (*writepage)(page, wbc, data);
if (unlikely(ret)) {
if (ret == AOP_WRITEPAGE_ACTIVATE) {
--
To unsubscribe from this list: send the line "unsubscribe linux-fsdevel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
