Re: [PATCH V5 06/10] Per-memcg background reclaim.

[Minchan Kim <minchan.kim@gmail.com>]

On Sat, Apr 16, 2011 at 8:23 AM, Ying Han <yinghan@google.com> wrote:
> 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 invokes balance_pgdat_node() for all nodes on the system, which
> is another new function performs background reclaim per node. After reclaiming
> each node, it checks mem_cgroup_watermark_ok() and breaks the priority loop if
> it returns true.
>
> changelog v5..v4:
> 1. remove duplicate check on nodes_empty()
> 2. add logic to check if the per-memcg lru is empty on the zone.
> 3. make per-memcg kswapd to reclaim SWAP_CLUSTER_MAX per zone. It make senses
> since it helps to balance the pressure across zones within the memcg.
>
> changelog v4..v3:
> 1. split the select_victim_node and zone_unreclaimable to a seperate patches
> 2. remove the logic tries to do zone balancing.
>
> changelog v3..v2:
> 1. change mz->all_unreclaimable to be boolean.
> 2. define ZONE_RECLAIMABLE_RATE macro shared by zone and per-memcg reclaim.
> 3. some more clean-up.
>
> changelog v2..v1:
> 1. move the per-memcg per-zone clear_unreclaimable into uncharge stage.
> 2. shared the kswapd_run/kswapd_stop for per-memcg and global background
> reclaim.
> 3. name the per-memcg memcg as "memcg-id" (css->id). And the global kswapd
> keeps the same name.
> 4. fix a race on kswapd_stop while the per-memcg-per-zone info could be accessed
> after freeing.
> 5. add the fairness in zonelist where memcg remember the last zone reclaimed
> from.
>
> Signed-off-by: Ying Han <yinghan@google.com>
> ---
>  mm/vmscan.c |  157 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
>  1 files changed, 157 insertions(+), 0 deletions(-)
>
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index 06036d2..39e6300 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -47,6 +47,8 @@
>
>  #include <linux/swapops.h>
>
> +#include <linux/res_counter.h>
> +
>  #include "internal.h"
>
>  #define CREATE_TRACE_POINTS
> @@ -111,6 +113,8 @@ struct scan_control {
>         * are scanned.
>         */
>        nodemask_t      *nodemask;
> +
> +       int priority;
>  };
>
>  #define lru_to_page(_head) (list_entry((_head)->prev, struct page, lru))
> @@ -2631,11 +2635,164 @@ static void kswapd_try_to_sleep(struct kswapd *kswapd_p, int order,
>        finish_wait(wait_h, &wait);
>  }
>
> +#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.
> + */
> +static void balance_pgdat_node(pg_data_t *pgdat, int order,
> +                                       struct scan_control *sc)
> +{
> +       int i;
> +       unsigned long total_scanned = 0;
> +       struct mem_cgroup *mem_cont = sc->mem_cgroup;
> +       int priority = sc->priority;
> +       enum lru_list l;
> +
> +       /*
> +        * 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 < pgdat->nr_zones; i++) {
> +               struct zone *zone = pgdat->node_zones + i;
> +               unsigned long scan = 0;
> +
> +               for_each_evictable_lru(l)
> +                       scan += mem_cgroup_zone_nr_pages(mem_cont, zone, l);
> +
> +               if (!populated_zone(zone) || !scan)
> +                       continue;

Do we really need this double check?
Isn't only _scan_ check enough?
And shouldn't we consider non-swap case?

> +
> +               sc->nr_scanned = 0;
> +               shrink_zone(priority, zone, sc);
> +               total_scanned += sc->nr_scanned;
> +
> +               /*
> +                * 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;

I don't want to add more random write any more although we don't have
a trouble of real memory shortage.
Do you have any reason to reclaim memory urgently as writing dirty pages?
Maybe if we wait a little bit of time, flusher would write out the page.

> +               }
> +       }
> +
> +       sc->nr_scanned = total_scanned;
> +       return;

unnecessary return.

> +}
> +
> +/*
> + * Per cgroup background reclaim.
> + * TODO: Take off the order since memcg always do order 0
> + */
> +static unsigned long balance_mem_cgroup_pgdat(struct mem_cgroup *mem_cont,
> +                                             int order)
> +{
> +       int i, nid;
> +       int start_node;
> +       int priority;
> +       bool wmark_ok;
> +       int loop;
> +       pg_data_t *pgdat;
> +       nodemask_t do_nodes;
> +       unsigned long total_scanned;
> +       struct scan_control sc = {
> +               .gfp_mask = GFP_KERNEL,
> +               .may_unmap = 1,
> +               .may_swap = 1,
> +               .nr_to_reclaim = SWAP_CLUSTER_MAX,
> +               .swappiness = vm_swappiness,
> +               .order = order,
> +               .mem_cgroup = mem_cont,
> +       };
> +
> +loop_again:
> +       do_nodes = NODE_MASK_NONE;
> +       sc.may_writepage = !laptop_mode;

I think it depends on urgency(ie, priority, reclaim
ratio(#reclaim/#scanning) or something), not laptop_mode in case of
memcg.
As I said earlier,it wold be better to avoid random write.

> +       sc.nr_reclaimed = 0;
> +       total_scanned = 0;
> +
> +       for (priority = DEF_PRIORITY; priority >= 0; priority--) {
> +               sc.priority = priority;
> +               wmark_ok = false;
> +               loop = 0;
> +
> +               /* The swap token gets in the way of swapout... */
> +               if (!priority)
> +                       disable_swap_token();
> +
> +               if (priority == DEF_PRIORITY)
> +                       do_nodes = node_states[N_ONLINE];
> +
> +               while (1) {
> +                       nid = mem_cgroup_select_victim_node(mem_cont,
> +                                                       &do_nodes);
> +
> +                       /* Indicate we have cycled the nodelist once

Fix comment style.

> +                        * TODO: we might add MAX_RECLAIM_LOOP for preventing
> +                        * kswapd burning cpu cycles.
> +                        */
> +                       if (loop == 0) {
> +                               start_node = nid;
> +                               loop++;
> +                       } else if (nid == start_node)
> +                               break;
> +
> +                       pgdat = NODE_DATA(nid);
> +                       balance_pgdat_node(pgdat, order, &sc);
> +                       total_scanned += sc.nr_scanned;
> +
> +                       /* Set the node which has at least

Fix comment style.

> +                        * one reclaimable zone
> +                        */
> +                       for (i = pgdat->nr_zones - 1; i >= 0; i--) {
> +                               struct zone *zone = pgdat->node_zones + i;
> +
> +                               if (!populated_zone(zone))
> +                                       continue;
> +                       }

I can't understand your comment and logic.
The comment mentioned reclaimable zone but the logic checks just
populated_zone. What's meaning?

> +                       if (i < 0)
> +                               node_clear(nid, do_nodes);
> +
> +                       if (mem_cgroup_watermark_ok(mem_cont,
> +                                                       CHARGE_WMARK_HIGH)) {
> +                               wmark_ok = true;
> +                               goto out;
> +                       }
> +
> +                       if (nodes_empty(do_nodes)) {
> +                               wmark_ok = true;
> +                               goto out;
> +                       }
> +               }
> +
> +               if (total_scanned && priority < DEF_PRIORITY - 2)
> +                       congestion_wait(WRITE, HZ/10);
> +
> +               if (sc.nr_reclaimed >= SWAP_CLUSTER_MAX)
> +                       break;
> +       }
> +out:
> +       if (!wmark_ok) {
> +               cond_resched();
> +
> +               try_to_freeze();
> +
> +               goto loop_again;
> +       }
> +
> +       return sc.nr_reclaimed;
> +}
> +#else
>  static unsigned long balance_mem_cgroup_pgdat(struct mem_cgroup *mem_cont,
>                                                        int order)
>  {
>        return 0;
>  }
> +#endif
>
>  /*
>  * The background pageout daemon, started as a kernel thread
> --
> 1.7.3.1
>
>



-- 
Kind regards,
Minchan Kim