#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/mm.h>
+#include <linux/sched/mm.h>
#include <linux/module.h>
#include <linux/gfp.h>
#include <linux/kernel_stat.h>
/* The highest zone to isolate pages for reclaim from */
enum zone_type reclaim_idx;
+ /* Writepage batching in laptop mode; RECLAIM_WRITE */
unsigned int may_writepage:1;
/* Can mapped pages be reclaimed? */
* throttling so we could easily OOM just because too many
* pages are in writeback and there is nothing else to
* reclaim. Wait for the writeback to complete.
+ *
+ * In cases 1) and 2) we activate the pages to get them out of
+ * the way while we continue scanning for clean pages on the
+ * inactive list and refilling from the active list. The
+ * observation here is that waiting for disk writes is more
+ * expensive than potentially causing reloads down the line.
+ * Since they're marked for immediate reclaim, they won't put
+ * memory pressure on the cache working set any longer than it
+ * takes to write them to disk.
*/
if (PageWriteback(page)) {
/* Case 1 above */
PageReclaim(page) &&
test_bit(PGDAT_WRITEBACK, &pgdat->flags)) {
nr_immediate++;
- goto keep_locked;
+ goto activate_locked;
/* Case 2 above */
} else if (sane_reclaim(sc) ||
*/
SetPageReclaim(page);
nr_writeback++;
- goto keep_locked;
+ goto activate_locked;
/* Case 3 above */
} else {
if (PageDirty(page)) {
/*
- * Only kswapd can writeback filesystem pages to
- * avoid risk of stack overflow but only writeback
- * if many dirty pages have been encountered.
+ * Only kswapd can writeback filesystem pages
+ * to avoid risk of stack overflow. But avoid
+ * injecting inefficient single-page IO into
+ * flusher writeback as much as possible: only
+ * write pages when we've encountered many
+ * dirty pages, and when we've already scanned
+ * the rest of the LRU for clean pages and see
+ * the same dirty pages again (PageReclaim).
*/
if (page_is_file_cache(page) &&
- (!current_is_kswapd() ||
- !test_bit(PGDAT_DIRTY, &pgdat->flags))) {
+ (!current_is_kswapd() || !PageReclaim(page) ||
+ !test_bit(PGDAT_DIRTY, &pgdat->flags))) {
/*
* Immediately reclaim when written back.
* Similar in principal to deactivate_page()
inc_node_page_state(page, NR_VMSCAN_IMMEDIATE);
SetPageReclaim(page);
- goto keep_locked;
+ goto activate_locked;
}
if (references == PAGEREF_RECLAIM_CLEAN)
* wants to isolate pages it will be able to operate on without
* blocking - clean pages for the most part.
*
- * ISOLATE_CLEAN means that only clean pages should be isolated. This
- * is used by reclaim when it is cannot write to backing storage
- *
* ISOLATE_ASYNC_MIGRATE is used to indicate that it only wants to pages
* that it is possible to migrate without blocking
*/
- if (mode & (ISOLATE_CLEAN|ISOLATE_ASYNC_MIGRATE)) {
+ if (mode & ISOLATE_ASYNC_MIGRATE) {
/* All the caller can do on PageWriteback is block */
if (PageWriteback(page))
return ret;
if (PageDirty(page)) {
struct address_space *mapping;
- /* ISOLATE_CLEAN means only clean pages */
- if (mode & ISOLATE_CLEAN)
- return ret;
-
/*
* Only pages without mappings or that have a
* ->migratepage callback are possible to migrate
if (!sc->may_unmap)
isolate_mode |= ISOLATE_UNMAPPED;
- if (!sc->may_writepage)
- isolate_mode |= ISOLATE_CLEAN;
spin_lock_irq(&pgdat->lru_lock);
/*
* If dirty pages are scanned that are not queued for IO, it
- * implies that flushers are not keeping up. In this case, flag
- * the pgdat PGDAT_DIRTY and kswapd will start writing pages from
- * reclaim context.
+ * implies that flushers are not doing their job. This can
+ * happen when memory pressure pushes dirty pages to the end of
+ * the LRU before the dirty limits are breached and the dirty
+ * data has expired. It can also happen when the proportion of
+ * dirty pages grows not through writes but through memory
+ * pressure reclaiming all the clean cache. And in some cases,
+ * the flushers simply cannot keep up with the allocation
+ * rate. Nudge the flusher threads in case they are asleep, but
+ * also allow kswapd to start writing pages during reclaim.
*/
- if (stat.nr_unqueued_dirty == nr_taken)
+ if (stat.nr_unqueued_dirty == nr_taken) {
+ wakeup_flusher_threads(0, WB_REASON_VMSCAN);
set_bit(PGDAT_DIRTY, &pgdat->flags);
+ }
/*
* If kswapd scans pages marked marked for immediate
if (!sc->may_unmap)
isolate_mode |= ISOLATE_UNMAPPED;
- if (!sc->may_writepage)
- isolate_mode |= ISOLATE_CLEAN;
spin_lock_irq(&pgdat->lru_lock);
} while (should_continue_reclaim(pgdat, sc->nr_reclaimed - nr_reclaimed,
sc->nr_scanned - nr_scanned, sc));
+ /*
+ * Kswapd gives up on balancing particular nodes after too
+ * many failures to reclaim anything from them and goes to
+ * sleep. On reclaim progress, reset the failure counter. A
+ * successful direct reclaim run will revive a dormant kswapd.
+ */
+ if (reclaimable)
+ pgdat->kswapd_failures = 0;
+
return reclaimable;
}
GFP_KERNEL | __GFP_HARDWALL))
continue;
- if (sc->priority != DEF_PRIORITY &&
- !pgdat_reclaimable(zone->zone_pgdat))
- continue; /* Let kswapd poll it */
-
/*
* If we already have plenty of memory free for
* compaction in this zone, don't free any more.
struct scan_control *sc)
{
int initial_priority = sc->priority;
- unsigned long total_scanned = 0;
- unsigned long writeback_threshold;
retry:
delayacct_freepages_start();
sc->nr_scanned = 0;
shrink_zones(zonelist, sc);
- total_scanned += sc->nr_scanned;
if (sc->nr_reclaimed >= sc->nr_to_reclaim)
break;
*/
if (sc->priority < DEF_PRIORITY - 2)
sc->may_writepage = 1;
-
- /*
- * Try to write back as many pages as we just scanned. This
- * tends to cause slow streaming writers to write data to the
- * disk smoothly, at the dirtying rate, which is nice. But
- * that's undesirable in laptop mode, where we *want* lumpy
- * writeout. So in laptop mode, write out the whole world.
- */
- writeback_threshold = sc->nr_to_reclaim + sc->nr_to_reclaim / 2;
- if (total_scanned > writeback_threshold) {
- wakeup_flusher_threads(laptop_mode ? 0 : total_scanned,
- WB_REASON_TRY_TO_FREE_PAGES);
- sc->may_writepage = 1;
- }
} while (--sc->priority >= 0);
delayacct_freepages_end();
return 0;
}
-static bool pfmemalloc_watermark_ok(pg_data_t *pgdat)
+static bool allow_direct_reclaim(pg_data_t *pgdat)
{
struct zone *zone;
unsigned long pfmemalloc_reserve = 0;
int i;
bool wmark_ok;
+ if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES)
+ return true;
+
for (i = 0; i <= ZONE_NORMAL; i++) {
zone = &pgdat->node_zones[i];
- if (!managed_zone(zone) ||
- pgdat_reclaimable_pages(pgdat) == 0)
+ if (!managed_zone(zone))
+ continue;
+
+ if (!zone_reclaimable_pages(zone))
continue;
pfmemalloc_reserve += min_wmark_pages(zone);
/* Throttle based on the first usable node */
pgdat = zone->zone_pgdat;
- if (pfmemalloc_watermark_ok(pgdat))
+ if (allow_direct_reclaim(pgdat))
goto out;
break;
}
*/
if (!(gfp_mask & __GFP_FS)) {
wait_event_interruptible_timeout(pgdat->pfmemalloc_wait,
- pfmemalloc_watermark_ok(pgdat), HZ);
+ allow_direct_reclaim(pgdat), HZ);
goto check_pending;
}
/* Throttle until kswapd wakes the process */
wait_event_killable(zone->zone_pgdat->pfmemalloc_wait,
- pfmemalloc_watermark_ok(pgdat));
+ allow_direct_reclaim(pgdat));
check_pending:
if (fatal_signal_pending(current))
*/
clear_bit(PGDAT_CONGESTED, &zone->zone_pgdat->flags);
clear_bit(PGDAT_DIRTY, &zone->zone_pgdat->flags);
+ clear_bit(PGDAT_WRITEBACK, &zone->zone_pgdat->flags);
return true;
}
/*
* The throttled processes are normally woken up in balance_pgdat() as
- * soon as pfmemalloc_watermark_ok() is true. But there is a potential
+ * soon as allow_direct_reclaim() is true. But there is a potential
* race between when kswapd checks the watermarks and a process gets
* throttled. There is also a potential race if processes get
* throttled, kswapd wakes, a large process exits thereby balancing the
if (waitqueue_active(&pgdat->pfmemalloc_wait))
wake_up_all(&pgdat->pfmemalloc_wait);
+ /* Hopeless node, leave it to direct reclaim */
+ if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES)
+ return true;
+
for (i = 0; i <= classzone_idx; i++) {
struct zone *zone = pgdat->node_zones + i;
count_vm_event(PAGEOUTRUN);
do {
+ unsigned long nr_reclaimed = sc.nr_reclaimed;
bool raise_priority = true;
- sc.nr_reclaimed = 0;
sc.reclaim_idx = classzone_idx;
/*
* If we're getting trouble reclaiming, start doing writepage
* even in laptop mode.
*/
- if (sc.priority < DEF_PRIORITY - 2 || !pgdat_reclaimable(pgdat))
+ if (sc.priority < DEF_PRIORITY - 2)
sc.may_writepage = 1;
/* Call soft limit reclaim before calling shrink_node. */
* able to safely make forward progress. Wake them
*/
if (waitqueue_active(&pgdat->pfmemalloc_wait) &&
- pfmemalloc_watermark_ok(pgdat))
+ allow_direct_reclaim(pgdat))
wake_up_all(&pgdat->pfmemalloc_wait);
/* Check if kswapd should be suspending */
* Raise priority if scanning rate is too low or there was no
* progress in reclaiming pages
*/
- if (raise_priority || !sc.nr_reclaimed)
+ nr_reclaimed = sc.nr_reclaimed - nr_reclaimed;
+ if (raise_priority || !nr_reclaimed)
sc.priority--;
} while (sc.priority >= 1);
+ if (!sc.nr_reclaimed)
+ pgdat->kswapd_failures++;
+
out:
/*
* Return the order kswapd stopped reclaiming at as
if (!waitqueue_active(&pgdat->kswapd_wait))
return;
+ /* Hopeless node, leave it to direct reclaim */
+ if (pgdat->kswapd_failures >= MAX_RECLAIM_RETRIES)
+ return;
+
/* Only wake kswapd if all zones are unbalanced */
for (z = 0; z <= classzone_idx; z++) {
zone = pgdat->node_zones + z;
sum_zone_node_page_state(pgdat->node_id, NR_SLAB_RECLAIMABLE) <= pgdat->min_slab_pages)
return NODE_RECLAIM_FULL;
- if (!pgdat_reclaimable(pgdat))
- return NODE_RECLAIM_FULL;
-
/*
* Do not scan if the allocation should not be delayed.
*/