On Mon, 25 Apr 2011 21:59:06 -0700
Ying Han <
yinghan@google.com> wrote:
> On Mon, Apr 25, 2011 at 2:36 AM, KAMEZAWA Hiroyuki
> <
kamezawa.hiroyu@jp.fujitsu.com> wrote:
> > Following patch will chagnge the logic. This is a core.
> > ==
> > This is the main loop of per-memcg background reclaim which is implemented in
> > function balance_mem_cgroup_pgdat().
> >
> > The function performs a priority loop similar to global reclaim. During each
> > iteration it frees memory from a selected victim node.
> > After reclaiming enough pages or scanning enough pages, it returns and find
> > next work with round-robin.
> >
> > changelog v8b..v7
> > 1. reworked for using work_queue rather than threads.
> > 2. changed shrink_mem_cgroup algorithm to fit workqueue. In short, avoid
> > long running and allow quick round-robin and unnecessary write page.
> > When a thread make pages dirty continuously, write back them by flusher
> > is far faster than writeback by background reclaim. This detail will
> > be fixed when dirty_ratio implemented. The logic around this will be
> > revisited in following patche.
> >
> > Signed-off-by: Ying Han <
yinghan@google.com>
> > Signed-off-by: KAMEZAWA Hiroyuki <
kamezawa.hiroyu@jp.fujitsu.com>
> > ---
> > include/linux/memcontrol.h | 11 ++++
> > mm/memcontrol.c | 44 ++++++++++++++---
> > mm/vmscan.c | 115 +++++++++++++++++++++++++++++++++++++++++++++
> > 3 files changed, 162 insertions(+), 8 deletions(-)
> >
> > Index: memcg/include/linux/memcontrol.h
> > ===================================================================
> > --- memcg.orig/include/linux/memcontrol.h
> > +++ memcg/include/linux/memcontrol.h
> > @@ -89,6 +89,8 @@ extern int mem_cgroup_last_scanned_node(
> > extern int mem_cgroup_select_victim_node(struct mem_cgroup *mem,
> > const nodemask_t *nodes);
> >
> > +unsigned long shrink_mem_cgroup(struct mem_cgroup *mem);
> > +
> > static inline
> > int mm_match_cgroup(const struct mm_struct *mm, const struct mem_cgroup *cgroup)
> > {
> > @@ -112,6 +114,9 @@ extern void mem_cgroup_end_migration(str
> > */
> > int mem_cgroup_inactive_anon_is_low(struct mem_cgroup *memcg);
> > int mem_cgroup_inactive_file_is_low(struct mem_cgroup *memcg);
> > +unsigned int mem_cgroup_swappiness(struct mem_cgroup *memcg);
> > +unsigned long mem_cgroup_zone_reclaimable_pages(struct mem_cgroup *memcg,
> > + int nid, int zone_idx);
> > unsigned long mem_cgroup_zone_nr_pages(struct mem_cgroup *memcg,
> > struct zone *zone,
> > enum lru_list lru);
> > @@ -310,6 +315,12 @@ mem_cgroup_inactive_file_is_low(struct m
> > }
> >
> > static inline unsigned long
> > +mem_cgroup_zone_reclaimable_pages(struct mem_cgroup *memcg, int nid, int zone_idx)
> > +{
> > + return 0;
> > +}
> > +
> > +static inline unsigned long
> > mem_cgroup_zone_nr_pages(struct mem_cgroup *memcg, struct zone *zone,
> > enum lru_list lru)
> > {
> > Index: memcg/mm/memcontrol.c
> > ===================================================================
> > --- memcg.orig/mm/memcontrol.c
> > +++ memcg/mm/memcontrol.c
> > @@ -1166,6 +1166,23 @@ int mem_cgroup_inactive_file_is_low(stru
> > return (active > inactive);
> > }
> >
> > +unsigned long mem_cgroup_zone_reclaimable_pages(struct mem_cgroup *memcg,
> > + int nid, int zone_idx)
> > +{
> > + int nr;
> > + struct mem_cgroup_per_zone *mz =
> > + mem_cgroup_zoneinfo(memcg, nid, zone_idx);
> > +
> > + nr = MEM_CGROUP_ZSTAT(mz, NR_ACTIVE_FILE) +
> > + MEM_CGROUP_ZSTAT(mz, NR_INACTIVE_FILE);
> > +
> > + if (nr_swap_pages > 0)
> > + nr += MEM_CGROUP_ZSTAT(mz, NR_ACTIVE_ANON) +
> > + MEM_CGROUP_ZSTAT(mz, NR_INACTIVE_ANON);
> > +
> > + return nr;
> > +}
> > +
> > unsigned long mem_cgroup_zone_nr_pages(struct mem_cgroup *memcg,
> > struct zone *zone,
> > enum lru_list lru)
> > @@ -1286,7 +1303,7 @@ static unsigned long mem_cgroup_margin(s
> > return margin >> PAGE_SHIFT;
> > }
> >
> > -static unsigned int get_swappiness(struct mem_cgroup *memcg)
> > +unsigned int mem_cgroup_swappiness(struct mem_cgroup *memcg)
> > {
> > struct cgroup *cgrp = memcg->css.cgroup;
> >
> > @@ -1595,14 +1612,15 @@ static int mem_cgroup_hierarchical_recla
> > /* we use swappiness of local cgroup */
> > if (check_soft) {
> > ret = mem_cgroup_shrink_node_zone(victim, gfp_mask,
> > - noswap, get_swappiness(victim), zone,
> > + noswap, mem_cgroup_swappiness(victim), zone,
> > &nr_scanned);
> > *total_scanned += nr_scanned;
> > mem_cgroup_soft_steal(victim, ret);
> > mem_cgroup_soft_scan(victim, nr_scanned);
> > } else
> > ret = try_to_free_mem_cgroup_pages(victim, gfp_mask,
> > - noswap, get_swappiness(victim));
> > + noswap,
> > + mem_cgroup_swappiness(victim));
> > css_put(&victim->css);
> > /*
> > * At shrinking usage, we can't check we should stop here or
> > @@ -1628,15 +1646,25 @@ static int mem_cgroup_hierarchical_recla
> > int
> > mem_cgroup_select_victim_node(struct mem_cgroup *mem, const nodemask_t *nodes)
> > {
> > - int next_nid;
> > + int next_nid, i;
> > int last_scanned;
> >
> > last_scanned = mem->last_scanned_node;
> > - next_nid = next_node(last_scanned, *nodes);
> > + next_nid = last_scanned;
> > +rescan:
> > + next_nid = next_node(next_nid, *nodes);
> >
> > if (next_nid == MAX_NUMNODES)
> > next_nid = first_node(*nodes);
> >
> > + /* If no page on this node, skip */
> > + for (i = 0; i < MAX_NR_ZONES; i++)
> > + if (mem_cgroup_zone_reclaimable_pages(mem, next_nid, i))
> > + break;
> > +
> > + if (next_nid != last_scanned && (i == MAX_NR_ZONES))
> > + goto rescan;
> > +
> > mem->last_scanned_node = next_nid;
> >
> > return next_nid;
> > @@ -3649,7 +3677,7 @@ try_to_free:
> > goto out;
> > }
> > progress = try_to_free_mem_cgroup_pages(mem, GFP_KERNEL,
> > - false, get_swappiness(mem));
> > + false, mem_cgroup_swappiness(mem));
> > if (!progress) {
> > nr_retries--;
> > /* maybe some writeback is necessary */
> > @@ -4073,7 +4101,7 @@ static u64 mem_cgroup_swappiness_read(st
> > {
> > struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
> >
> > - return get_swappiness(memcg);
> > + return mem_cgroup_swappiness(memcg);
> > }
> >
> > static int mem_cgroup_swappiness_write(struct cgroup *cgrp, struct cftype *cft,
> > @@ -4849,7 +4877,7 @@ mem_cgroup_create(struct cgroup_subsys *
> > INIT_LIST_HEAD(&mem->oom_notify);
> >
> > if (parent)
> > - mem->swappiness = get_swappiness(parent);
> > + mem->swappiness = mem_cgroup_swappiness(parent);
> > atomic_set(&mem->refcnt, 1);
> > mem->move_charge_at_immigrate = 0;
> > mutex_init(&mem->thresholds_lock);
> > Index: memcg/mm/vmscan.c
> > ===================================================================
> > --- memcg.orig/mm/vmscan.c
> > +++ memcg/mm/vmscan.c
> > @@ -42,6 +42,7 @@
> > #include <linux/delayacct.h>
> > #include <linux/sysctl.h>
> > #include <linux/oom.h>
> > +#include <linux/res_counter.h>
> >
> > #include <asm/tlbflush.h>
> > #include <asm/div64.h>
> > @@ -2308,6 +2309,120 @@ static bool sleeping_prematurely(pg_data
> > return !all_zones_ok;
> > }
> >
> > +#ifdef CONFIG_CGROUP_MEM_RES_CTLR
> > +/*
> > + * The function is used for per-memcg LRU. It scanns all the zones of the
> > + * node and returns the nr_scanned and nr_reclaimed.
> > + */
> > +/*
> > + * Limit of scanning per iteration. For round-robin.
> > + */
> > +#define MEMCG_BGSCAN_LIMIT (2048)
> > +
> > +static void
> > +shrink_memcg_node(int nid, int priority, struct scan_control *sc)
> > +{
> > + unsigned long total_scanned = 0;
> > + struct mem_cgroup *mem_cont = sc->mem_cgroup;
> > + int i;
> > +
> > + /*
> > + * This dma->highmem order is consistant with global reclaim.
> > + * We do this because the page allocator works in the opposite
> > + * direction although memcg user pages are mostly allocated at
> > + * highmem.
> > + */
> > + for (i = 0;
> > + (i < NODE_DATA(nid)->nr_zones) &&
> > + (total_scanned < MEMCG_BGSCAN_LIMIT);
> > + i++) {
> > + struct zone *zone = NODE_DATA(nid)->node_zones + i;
> > + struct zone_reclaim_stat *zrs;
> > + unsigned long scan, rotate;
> > +
> > + if (!populated_zone(zone))
> > + continue;
> > + scan = mem_cgroup_zone_reclaimable_pages(mem_cont, nid, i);
> > + if (!scan)
> > + continue;
> > + /* If recent memory reclaim on this zone doesn't get good */
> > + zrs = get_reclaim_stat(zone, sc);
> > + scan = zrs->recent_scanned[0] + zrs->recent_scanned[1];
> > + rotate = zrs->recent_rotated[0] + zrs->recent_rotated[1];
> > +
> > + if (rotate > scan/2)
> > + sc->may_writepage = 1;
> > +
> > + sc->nr_scanned = 0;
> > + shrink_zone(priority, zone, sc);
> > + total_scanned += sc->nr_scanned;
> > + sc->may_writepage = 0;
> > + }
> > + sc->nr_scanned = total_scanned;
> > +}
>
> I see the MEMCG_BGSCAN_LIMIT is a newly defined macro from previous
> post. So, now the number of pages to scan is capped on 2k for each
> memcg, and does it make difference on big vs small cgroup?
>