lkml.org 
[lkml]   [2006]   [Apr]   [21]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
SubjectUpdated version of shrink_all_memory tweaks.
Date
Hi.

I give the shrink_all_memory tweaks a try today, and fixed a couple of
mistakes that meant too much memory was still freed. With this version of the
patch, you get at most exactly what you ask for.

This version is for 2.6.17-rc2. Just in case they're not obvious, the changes
are limited to taking account of what has already been freed in subsequent
calls to shrink_all_zones (swap_cluster_max is updated, and nr_to_scan is
modified similarly).

Regards,

Nigel

kernel/power/swsusp.c | 10 +-
mm/vmscan.c | 216
+++++++++++++++++++++++++++++++++++++-------------
2 files changed, 168 insertions(+), 58 deletions(-)
diff -ruNp 9930-shrink-less-memory.patch-old/kernel/power/swsusp.c
9930-shrink-less-memory.patch-new/kernel/power/swsusp.c
--- 9930-shrink-less-memory.patch-old/kernel/power/swsusp.c 2006-04-21
19:53:52.000000000 +1000
+++ 9930-shrink-less-memory.patch-new/kernel/power/swsusp.c 2006-04-20
08:39:47.000000000 +1000
@@ -178,6 +178,12 @@ void free_all_swap_pages(int swap, struc
*/

#define SHRINK_BITE 10000
+static inline unsigned long __shrink_memory(long tmp)
+{
+ if (tmp > SHRINK_BITE)
+ tmp = SHRINK_BITE;
+ return shrink_all_memory(tmp);
+}

int swsusp_shrink_memory(void)
{
@@ -200,12 +206,12 @@ int swsusp_shrink_memory(void)
if (!is_highmem(zone))
tmp -= zone->free_pages;
if (tmp > 0) {
- tmp = shrink_all_memory(SHRINK_BITE);
+ tmp = __shrink_memory(tmp);
if (!tmp)
return -ENOMEM;
pages += tmp;
} else if (size > image_size / PAGE_SIZE) {
- tmp = shrink_all_memory(SHRINK_BITE);
+ tmp = __shrink_memory(size - (image_size / PAGE_SIZE));
pages += tmp;
}
printk("\b%c", p[i++%4]);
diff -ruNp 9930-shrink-less-memory.patch-old/mm/vmscan.c
9930-shrink-less-memory.patch-new/mm/vmscan.c
--- 9930-shrink-less-memory.patch-old/mm/vmscan.c 2006-04-21
19:53:52.000000000 +1000
+++ 9930-shrink-less-memory.patch-new/mm/vmscan.c 2006-04-21
19:54:02.000000000 +1000
@@ -203,7 +203,7 @@ unsigned long shrink_slab(unsigned long
total_scan = shrinker->nr;
shrinker->nr = 0;

- while (total_scan >= SHRINK_BATCH) {
+ while (total_scan >= SHRINK_BATCH && ret < scanned) {
long this_scan = SHRINK_BATCH;
int shrink_ret;
int nr_before;
@@ -1021,10 +1021,6 @@ out:
* For kswapd, balance_pgdat() will work across all this node's zones until
* they are all at pages_high.
*
- * If `nr_pages' is non-zero then it is the number of pages which are to be
- * reclaimed, regardless of the zone occupancies. This is a software suspend
- * special.
- *
* Returns the number of pages which were actually freed.
*
* There is special handling here for zones which are full of pinned pages.
@@ -1042,10 +1038,8 @@ out:
* the page allocator fallback scheme to ensure that aging of pages is
balanced
* across the zones.
*/
-static unsigned long balance_pgdat(pg_data_t *pgdat, unsigned long nr_pages,
- int order)
+static unsigned long balance_pgdat(pg_data_t *pgdat, int order)
{
- unsigned long to_free = nr_pages;
int all_zones_ok;
int priority;
int i;
@@ -1055,7 +1049,7 @@ static unsigned long balance_pgdat(pg_da
struct scan_control sc = {
.gfp_mask = GFP_KERNEL,
.may_swap = 1,
- .swap_cluster_max = nr_pages ? nr_pages : SWAP_CLUSTER_MAX,
+ .swap_cluster_max = SWAP_CLUSTER_MAX,
};

loop_again:
@@ -1082,31 +1076,27 @@ loop_again:

all_zones_ok = 1;

- if (nr_pages == 0) {
- /*
- * Scan in the highmem->dma direction for the highest
- * zone which needs scanning
- */
- for (i = pgdat->nr_zones - 1; i >= 0; i--) {
- struct zone *zone = pgdat->node_zones + i;
+ /*
+ * Scan in the highmem->dma direction for the highest
+ * zone which needs scanning
+ */
+ for (i = pgdat->nr_zones - 1; i >= 0; i--) {
+ struct zone *zone = pgdat->node_zones + i;
+
+ if (!populated_zone(zone))
+ continue;

- if (!populated_zone(zone))
- continue;
+ if (zone->all_unreclaimable &&
+ priority != DEF_PRIORITY)
+ continue;

- if (zone->all_unreclaimable &&
- priority != DEF_PRIORITY)
- continue;
-
- if (!zone_watermark_ok(zone, order,
- zone->pages_high, 0, 0)) {
- end_zone = i;
- goto scan;
- }
+ if (!zone_watermark_ok(zone, order, zone->pages_high,
+ 0, 0)) {
+ end_zone = i;
+ goto scan;
}
- goto out;
- } else {
- end_zone = pgdat->nr_zones - 1;
}
+ goto out;
scan:
for (i = 0; i <= end_zone; i++) {
struct zone *zone = pgdat->node_zones + i;
@@ -1133,11 +1123,9 @@ scan:
if (zone->all_unreclaimable && priority != DEF_PRIORITY)
continue;

- if (nr_pages == 0) { /* Not software suspend */
- if (!zone_watermark_ok(zone, order,
- zone->pages_high, end_zone, 0))
- all_zones_ok = 0;
- }
+ if (!zone_watermark_ok(zone, order, zone->pages_high,
+ end_zone, 0))
+ all_zones_ok = 0;
zone->temp_priority = priority;
if (zone->prev_priority > priority)
zone->prev_priority = priority;
@@ -1162,8 +1150,6 @@ scan:
total_scanned > nr_reclaimed + nr_reclaimed / 2)
sc.may_writepage = 1;
}
- if (nr_pages && to_free > nr_reclaimed)
- continue; /* swsusp: need to do more work */
if (all_zones_ok)
break; /* kswapd: all done */
/*
@@ -1179,7 +1165,7 @@ scan:
* matches the direct reclaim path behaviour in terms of impact
* on zone->*_priority.
*/
- if ((nr_reclaimed >= SWAP_CLUSTER_MAX) && !nr_pages)
+ if (nr_reclaimed >= SWAP_CLUSTER_MAX)
break;
}
out:
@@ -1262,7 +1248,7 @@ static int kswapd(void *p)
}
finish_wait(&pgdat->kswapd_wait, &wait);

- balance_pgdat(pgdat, 0, order);
+ balance_pgdat(pgdat, order);
}
return 0;
}
@@ -1291,35 +1277,153 @@ void wakeup_kswapd(struct zone *zone, in

#ifdef CONFIG_PM
/*
- * Try to free `nr_pages' of memory, system-wide. Returns the number of
freed
- * pages.
+ * Helper function for shrink_all_memory(). Tries to reclaim 'nr_pages'
pages
+ * from LRU lists system-wide, for given pass and priority, and returns the
+ * number of reclaimed pages
+ *
+ * For pass > 3 we also try to shrink the LRU lists that contain a few pages
+ */
+unsigned long shrink_all_zones(unsigned long nr_pages, int pass, int prio,
+ struct scan_control *sc)
+{
+ struct zone *zone;
+ unsigned long nr_to_scan, ret = 0;
+
+ for_each_zone(zone) {
+
+ if (!populated_zone(zone))
+ continue;
+
+ if (zone->all_unreclaimable && prio != DEF_PRIORITY)
+ continue;
+
+ /* For pass = 0 we don't shrink the active list */
+ if (pass > 0) {
+ zone->nr_scan_active += (zone->nr_active >> prio) + 1;
+ if (zone->nr_scan_active >= nr_pages || pass > 3) {
+ zone->nr_scan_active = 0;
+ nr_to_scan = min(nr_pages, zone->nr_active);
+ shrink_active_list(nr_to_scan, zone, sc);
+ }
+ }
+
+ zone->nr_scan_inactive += (zone->nr_inactive >> prio) + 1;
+ if (zone->nr_scan_inactive >= (nr_pages - ret) || pass > 3) {
+ zone->nr_scan_inactive = 0;
+ nr_to_scan = min(nr_pages - ret, zone->nr_inactive);
+ ret += shrink_inactive_list(nr_to_scan, zone, sc);
+ if (ret >= nr_pages)
+ return ret;
+ }
+ }
+
+ return ret;
+}
+
+/*
+ * Try to free `nr_pages' of memory, system-wide, and return the number of
+ * freed pages.
+ *
+ * Rather than trying to age LRUs the aim is to preserve the overall
+ * LRU order by reclaiming preferentially
+ * inactive > active > active referenced > active mapped
*/
unsigned long shrink_all_memory(unsigned long nr_pages)
{
- pg_data_t *pgdat;
- unsigned long nr_to_free = nr_pages;
+ unsigned long lru_pages, nr_slab;
unsigned long ret = 0;
- unsigned retry = 2;
- struct reclaim_state reclaim_state = {
- .reclaimed_slab = 0,
+ int swappiness = vm_swappiness, pass;
+ struct reclaim_state reclaim_state;
+ struct zone *zone;
+ struct scan_control sc = {
+ .gfp_mask = GFP_KERNEL,
+ .may_swap = 1,
+ .swap_cluster_max = nr_pages,
+ .may_writepage = 1,
};

current->reclaim_state = &reclaim_state;
-repeat:
- for_each_online_pgdat(pgdat) {
- unsigned long freed;

- freed = balance_pgdat(pgdat, nr_to_free, 0);
- ret += freed;
- nr_to_free -= freed;
- if ((long)nr_to_free <= 0)
+ lru_pages = 0;
+ for_each_zone(zone)
+ lru_pages += zone->nr_active + zone->nr_inactive;
+ nr_slab = read_page_state(nr_slab);
+ /* If slab caches are huge, it's better to hit them first */
+ while (nr_slab >= lru_pages) {
+ reclaim_state.reclaimed_slab = 0;
+ shrink_slab(nr_pages, sc.gfp_mask, lru_pages);
+ if (!reclaim_state.reclaimed_slab)
break;
+
+ ret += reclaim_state.reclaimed_slab;
+ if (ret >= nr_pages)
+ goto out;
+
+ nr_slab -= reclaim_state.reclaimed_slab;
}
- if (retry-- && ret < nr_pages) {
- blk_congestion_wait(WRITE, HZ/5);
- goto repeat;
+
+ /*
+ * We try to shrink LRUs in 5 passes:
+ * 0 = Reclaim from inactive_list only
+ * 1 = Reclaim from active list but don't reclaim mapped
+ * 2 = 2nd pass of type 1
+ * 3 = Reclaim mapped (normal reclaim)
+ * 4 = 2nd pass of type 3
+ */
+ for (pass = 0; pass < 5; pass++) {
+ int prio;
+
+ /* Needed for shrinking slab caches later on */
+ if (!lru_pages)
+ for_each_zone(zone) {
+ lru_pages += zone->nr_active;
+ lru_pages += zone->nr_inactive;
+ }
+
+ /* Force reclaiming mapped pages in the passes #3 and #4 */
+ if (pass > 2)
+ vm_swappiness = 100;
+
+ for (prio = DEF_PRIORITY; prio >= 0; prio--) {
+ unsigned long nr_to_scan = nr_pages - ret;
+
+ sc.nr_mapped = read_page_state(nr_mapped);
+ sc.nr_scanned = 0;
+ sc.swap_cluster_max = nr_pages - ret;
+
+ ret += shrink_all_zones(nr_to_scan, prio, pass, &sc);
+ if (ret >= nr_pages)
+ goto out;
+
+ reclaim_state.reclaimed_slab = 0;
+ shrink_slab(sc.nr_scanned, sc.gfp_mask, lru_pages);
+ ret += reclaim_state.reclaimed_slab;
+ if (ret >= nr_pages)
+ goto out;
+
+ if (sc.nr_scanned && prio < DEF_PRIORITY - 2)
+ blk_congestion_wait(WRITE, HZ / 10);
+ }
+
+ lru_pages = 0;
}
+
+
+ /*
+ * If ret = 0, we could not shrink LRUs, but there may be something
+ * in slab caches
+ */
+ if (!ret)
+ do {
+ reclaim_state.reclaimed_slab = 0;
+ shrink_slab(nr_pages, sc.gfp_mask, lru_pages);
+ ret += reclaim_state.reclaimed_slab;
+ } while (ret < nr_pages && reclaim_state.reclaimed_slab > 0);
+
+out:
current->reclaim_state = NULL;
+ vm_swappiness = swappiness;
+
return ret;
}
#endif[unhandled content-type:application/pgp-signature]
\
 
 \ /
  Last update: 2006-04-21 23:37    [W:0.041 / U:0.144 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site