参照元†
- pg_data_t *pgdat
- int order
返り値†
/*
* For kswapd, balance_pgdat() will work across all this node's zones until
* they are all at high_wmark_pages(zone).
*
* Returns the number of pages which were actually freed.
*
* There is special handling here for zones which are full of pinned pages.
* This can happen if the pages are all mlocked, or if they are all used by
* device drivers (say, ZONE_DMA). Or if they are all in use by hugetlb.
* What we do is to detect the case where all pages in the zone have been
* scanned twice and there has been zero successful reclaim. Mark the zone as
* dead and from now on, only perform a short scan. Basically we're polling
* the zone for when the problem goes away.
*
* kswapd scans the zones in the highmem->normal->dma direction. It skips
* zones which have free_pages > high_wmark_pages(zone), but once a zone is
* found to have free_pages <= high_wmark_pages(zone), we scan that zone and the
* lower zones regardless of the number of free pages in the lower zones. This
* interoperates with 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, int order)
{
int all_zones_ok;
int priority;
int i;
unsigned long total_scanned;
struct reclaim_state *reclaim_state = current->reclaim_state;
struct scan_control sc = {
.gfp_mask = GFP_KERNEL,
.may_unmap = 1,
.may_swap = 1,
/*
* kswapd doesn't want to be bailed out while reclaim. because
* we want to put equal scanning pressure on each zone.
*/
.nr_to_reclaim = ULONG_MAX,
.swappiness = vm_swappiness,
.order = order,
.mem_cgroup = NULL,
.isolate_pages = isolate_pages_global,
};
/*
* temp_priority is used to remember the scanning priority at which
* this zone was successfully refilled to
* free_pages == high_wmark_pages(zone).
*/
int temp_priority[MAX_NR_ZONES];
loop_again:
total_scanned = 0;
sc.nr_reclaimed = 0;
sc.may_writepage = !laptop_mode;
count_vm_event(PAGEOUTRUN);
for (i = 0; i < pgdat->nr_zones; i++)
temp_priority[i] = DEF_PRIORITY;
for (priority = DEF_PRIORITY; priority >= 0; priority--) {
int end_zone = 0; /* Inclusive. 0 = ZONE_DMA */
unsigned long lru_pages = 0;
int has_under_min_watermark_zone = 0;
/* The swap token gets in the way of swapout... */
if (!priority)
disable_swap_token();
all_zones_ok = 1;
/*
* 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 (zone_is_all_unreclaimable(zone) &&
priority != DEF_PRIORITY)
continue;
/*
* Do some background aging of the anon list, to give
* pages a chance to be referenced before reclaiming.
*/
if (inactive_anon_is_low(zone, &sc))
shrink_active_list(SWAP_CLUSTER_MAX, zone,
&sc, priority, 0);
if (!zone_watermark_ok(zone, order,
high_wmark_pages(zone), 0, 0)) {
end_zone = i;
break;
}
}
if (i < 0)
goto out;
for (i = 0; i <= end_zone; i++) {
struct zone *zone = pgdat->node_zones + i;
lru_pages += zone_reclaimable_pages(zone);
}
/*
* Now scan the zone in the dma->highmem direction, stopping
* at the last zone which needs scanning.
*
* We do this because the page allocator works in the opposite
* direction. This prevents the page allocator from allocating
* pages behind kswapd's direction of progress, which would
* cause too much scanning of the lower zones.
*/
for (i = 0; i <= end_zone; i++) {
struct zone *zone = pgdat->node_zones + i;
int nr_slab;
int nid, zid;
if (!populated_zone(zone))
continue;
if (zone_is_all_unreclaimable(zone) &&
priority != DEF_PRIORITY)
continue;
if (!zone_watermark_ok(zone, order,
high_wmark_pages(zone), end_zone, 0))
all_zones_ok = 0;
temp_priority[i] = priority;
sc.nr_scanned = 0;
note_zone_scanning_priority(zone, priority);
nid = pgdat->node_id;
zid = zone_idx(zone);
/*
* Call soft limit reclaim before calling shrink_zone.
* For now we ignore the return value
*/
mem_cgroup_soft_limit_reclaim(zone, order, sc.gfp_mask,
nid, zid);
/*
* We put equal pressure on every zone, unless one
* zone has way too many pages free already.
*/
if (!zone_watermark_ok(zone, order,
8*high_wmark_pages(zone), end_zone, 0))
shrink_zone(priority, zone, &sc);
reclaim_state->reclaimed_slab = 0;
nr_slab = shrink_slab(sc.nr_scanned, GFP_KERNEL,
lru_pages);
sc.nr_reclaimed += reclaim_state->reclaimed_slab;
total_scanned += sc.nr_scanned;
if (zone_is_all_unreclaimable(zone))
continue;
if (nr_slab == 0 && zone->pages_scanned >=
(zone_reclaimable_pages(zone) * 6))
zone_set_flag(zone,
ZONE_ALL_UNRECLAIMABLE);
/*
* If we've done a decent amount of scanning and
* the reclaim ratio is low, start doing writepage
* even in laptop mode
*/
if (total_scanned > SWAP_CLUSTER_MAX * 2 &&
total_scanned > sc.nr_reclaimed + sc.nr_reclaimed / 2)
sc.may_writepage = 1;
/*
* We are still under min water mark. it mean we have
* GFP_ATOMIC allocation failure risk. Hurry up!
*/
if (!zone_watermark_ok(zone, order, min_wmark_pages(zone),
end_zone, 0))
has_under_min_watermark_zone = 1;
}
if (all_zones_ok)
break; /* kswapd: all done */
/*
* OK, kswapd is getting into trouble. Take a nap, then take
* another pass across the zones.
*/
if (total_scanned && (priority < DEF_PRIORITY - 2)) {
if (has_under_min_watermark_zone)
count_vm_event(KSWAPD_SKIP_CONGESTION_WAIT);
else
congestion_wait(BLK_RW_ASYNC, HZ/10);
}
/*
* We do this so kswapd doesn't build up large priorities for
* example when it is freeing in parallel with allocators. It
* matches the direct reclaim path behaviour in terms of impact
* on zone->*_priority.
*/
if (sc.nr_reclaimed >= SWAP_CLUSTER_MAX)
break;
}
out:
/*
* Note within each zone the priority level at which this zone was
* brought into a happy state. So that the next thread which scans this
* zone will start out at that priority level.
*/
for (i = 0; i < pgdat->nr_zones; i++) {
struct zone *zone = pgdat->node_zones + i;
zone->prev_priority = temp_priority[i];
}
if (!all_zones_ok) {
cond_resched();
try_to_freeze();
/*
* Fragmentation may mean that the system cannot be
* rebalanced for high-order allocations in all zones.
* At this point, if nr_reclaimed < SWAP_CLUSTER_MAX,
* it means the zones have been fully scanned and are still
* not balanced. For high-order allocations, there is
* little point trying all over again as kswapd may
* infinite loop.
*
* Instead, recheck all watermarks at order-0 as they
* are the most important. If watermarks are ok, kswapd will go
* back to sleep. High-order users can still perform direct
* reclaim if they wish.
*/
if (sc.nr_reclaimed < SWAP_CLUSTER_MAX)
order = sc.order = 0;
goto loop_again;
}
return sc.nr_reclaimed;
}
コメント†