Commit c661b078 authored by Andy Whitcroft's avatar Andy Whitcroft Committed by Linus Torvalds
Browse files

synchronous lumpy reclaim: wait for page writeback when directly reclaiming contiguous areas

Lumpy reclaim works by selecting a lead page from the LRU list and then
selecting pages for reclaim from the order-aligned area of pages.  In the
situation were all pages in that region are inactive and not referenced by any
process over time, it works well.

In the situation where there is even light load on the system, the pages may
not free quickly.  Out of a area of 1024 pages, maybe only 950 of them are
freed when the allocation attempt occurs because lumpy reclaim returned early.
 This patch alters the behaviour of direct reclaim for large contiguous

The first attempt to call shrink_page_list() is asynchronous but if it fails,
the pages are submitted a second time and the calling process waits for the IO
to complete.  This may stall allocators waiting for contiguous memory but that
should be expected behaviour for high-order users.  It is preferable behaviour
to potentially queueing unnecessary areas for IO.  Note that kswapd will not
stall in this fashion.

[ update to version 2]
[ update to version 3]
Signed-off-by: default avatarMel Gorman <>
Signed-off-by: default avatarAndy Whitcroft <>
Signed-off-by: default avatarAndrew Morton <>
Signed-off-by: default avatarLinus Torvalds <>
parent e9187bdc
......@@ -271,6 +271,12 @@ static void handle_write_error(struct address_space *mapping,
/* Request for sync pageout. */
enum pageout_io {
/* possible outcome of pageout() */
typedef enum {
/* failed to write page out, page is locked */
......@@ -287,7 +293,8 @@ typedef enum {
* pageout is called by shrink_page_list() for each dirty page.
* Calls ->writepage().
static pageout_t pageout(struct page *page, struct address_space *mapping)
static pageout_t pageout(struct page *page, struct address_space *mapping,
enum pageout_io sync_writeback)
* If the page is dirty, only perform writeback if that write
......@@ -346,6 +353,15 @@ static pageout_t pageout(struct page *page, struct address_space *mapping)
* 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.
if (PageWriteback(page) && sync_writeback == PAGEOUT_IO_SYNC)
if (!PageWriteback(page)) {
/* synchronous write or broken a_ops? */
......@@ -423,7 +439,8 @@ cannot_free:
* shrink_page_list() returns the number of reclaimed pages
static unsigned long shrink_page_list(struct list_head *page_list,
struct scan_control *sc)
struct scan_control *sc,
enum pageout_io sync_writeback)
struct pagevec freed_pvec;
......@@ -458,8 +475,23 @@ static unsigned long shrink_page_list(struct list_head *page_list,
if (page_mapped(page) || PageSwapCache(page))
if (PageWriteback(page))
goto keep_locked;
may_enter_fs = (sc->gfp_mask & __GFP_FS) ||
(PageSwapCache(page) && (sc->gfp_mask & __GFP_IO));
if (PageWriteback(page)) {
* Synchronous reclaim is performed in two passes,
* first an asynchronous pass over the list to
* start parallel writeback, and a second synchronous
* pass to wait for the IO to complete. Wait here
* for any page for which writeback has already
* started.
if (sync_writeback == PAGEOUT_IO_SYNC && may_enter_fs)
goto keep_locked;
referenced = page_referenced(page, 1);
/* In active use or really unfreeable? Activate it. */
......@@ -478,8 +510,6 @@ static unsigned long shrink_page_list(struct list_head *page_list,
#endif /* CONFIG_SWAP */
mapping = page_mapping(page);
may_enter_fs = (sc->gfp_mask & __GFP_FS) ||
(PageSwapCache(page) && (sc->gfp_mask & __GFP_IO));
* The page is mapped into the page tables of one or more
......@@ -505,7 +535,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
goto keep_locked;
/* Page is dirty, try to write it out here */
switch(pageout(page, mapping)) {
switch (pageout(page, mapping, sync_writeback)) {
goto keep_locked;
......@@ -786,7 +816,29 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
nr_scanned += nr_scan;
nr_freed = shrink_page_list(&page_list, sc);
nr_freed = shrink_page_list(&page_list, sc, PAGEOUT_IO_ASYNC);
* If we are direct reclaiming for contiguous pages and we do
* not reclaim everything in the list, try again and wait
* for IO to complete. This will stall high-order allocations
* but that should be acceptable to the caller
if (nr_freed < nr_taken && !current_is_kswapd() &&
congestion_wait(WRITE, HZ/10);
* The attempt at page out may have made some
* of the pages active, mark them inactive again.
nr_active = clear_active_flags(&page_list);
count_vm_events(PGDEACTIVATE, nr_active);
nr_freed += shrink_page_list(&page_list, sc,
nr_reclaimed += nr_freed;
if (current_is_kswapd()) {
Supports Markdown
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment