| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <CAHbLzkoYDwU7wJWai1QzUA5DsJyQq1enLbWoCf2hRTaLBNCKtQ@mail.gmail.com>
Date: Thu, 20 Aug 2020 15:50:57 -0700
From: Yang Shi <shy828301@...il.com>
To: Dave Hansen <dave.hansen@...ux.intel.com>
Cc: Linux Kernel Mailing List <linux-kernel@...r.kernel.org>,
Yang Shi <yang.shi@...ux.alibaba.com>,
David Rientjes <rientjes@...gle.com>,
Huang Ying <ying.huang@...el.com>,
Dan Williams <dan.j.williams@...el.com>
Subject: Re: [RFC][PATCH 8/9] mm/vmscan: never demote for memcg reclaim
On Tue, Aug 18, 2020 at 11:52 AM Dave Hansen
<dave.hansen@...ux.intel.com> wrote:
>
>
> From: Dave Hansen <dave.hansen@...ux.intel.com>
>
> Global reclaim aims to reduce the amount of memory used on
> a given node or set of nodes. Migrating pages to another
> node serves this purpose.
>
> memcg reclaim is different. Its goal is to reduce the
> total memory consumption of the entire memcg, across all
> nodes. Migration does not assist memcg reclaim because
> it just moves page contents between nodes rather than
> actually reducing memory consumption.
>
> Signed-off-by: Dave Hansen <dave.hansen@...ux.intel.com>
> Suggested-by: Yang Shi <yang.shi@...ux.alibaba.com>
> Cc: David Rientjes <rientjes@...gle.com>
> Cc: Huang Ying <ying.huang@...el.com>
> Cc: Dan Williams <dan.j.williams@...el.com>
> ---
>
> b/mm/vmscan.c | 33 +++++++++++++++++++++++++--------
> 1 file changed, 25 insertions(+), 8 deletions(-)
>
> diff -puN mm/vmscan.c~never-demote-for-memcg-reclaim mm/vmscan.c
> --- a/mm/vmscan.c~never-demote-for-memcg-reclaim 2020-08-18 11:36:56.442583170 -0700
> +++ b/mm/vmscan.c 2020-08-18 11:36:56.447583170 -0700
> @@ -296,8 +296,11 @@ static bool writeback_throttling_sane(st
> #endif
>
> static inline bool can_reclaim_anon_pages(struct mem_cgroup *memcg,
> - int node_id)
> + int node_id,
> + struct scan_control *sc)
> {
> + bool in_cgroup_reclaim = false;
> +
> /* Always age anon pages when we have swap */
> if (memcg == NULL) {
> if (get_nr_swap_pages() > 0)
> @@ -307,8 +310,18 @@ static inline bool can_reclaim_anon_page
> return true;
> }
>
> - /* Also age anon pages if we can auto-migrate them */
> - if (next_demotion_node(node_id) >= 0)
> + /* Can only be in memcg reclaim in paths with valid 'sc': */
This comment looks not right. The global reclaim also has valid 'sc'
but just with NULL target_mem_cgroup.
> + if (sc && cgroup_reclaim(sc))
> + in_cgroup_reclaim = true;
> +
> + /*
> + * Also age anon pages if we can auto-migrate them.
> + *
> + * Migrating a page does not reduce comsumption of a
s/comsuption/consumption
> + * memcg so should not be performed when in memcg
> + * reclaim.
> + */
> + if (!in_cgroup_reclaim && (next_demotion_node(node_id) >= 0))
> return true;
>
> /* No way to reclaim anon pages */
> @@ -326,7 +339,7 @@ unsigned long zone_reclaimable_pages(str
>
> nr = zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_FILE) +
> zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_FILE);
> - if (can_reclaim_anon_pages(NULL, zone_to_nid(zone)))
> + if (can_reclaim_anon_pages(NULL, zone_to_nid(zone), NULL))
> nr += zone_page_state_snapshot(zone, NR_ZONE_INACTIVE_ANON) +
> zone_page_state_snapshot(zone, NR_ZONE_ACTIVE_ANON);
>
> @@ -1070,6 +1083,10 @@ bool migrate_demote_page_ok(struct page
> VM_BUG_ON_PAGE(PageHuge(page), page);
> VM_BUG_ON_PAGE(PageLRU(page), page);
>
> + /* It is pointless to do demotion in memcg reclaim */
> + if (cgroup_reclaim(sc))
> + return false;
> +
> if (next_nid == NUMA_NO_NODE)
> return false;
> if (PageTransHuge(page) && !thp_migration_supported())
> @@ -2369,7 +2386,7 @@ static void get_scan_count(struct lruvec
> enum lru_list lru;
>
> /* If we have no swap space, do not bother scanning anon pages. */
> - if (!sc->may_swap || !can_reclaim_anon_pages(memcg, pgdat->node_id)) {
> + if (!sc->may_swap || !can_reclaim_anon_pages(memcg, pgdat->node_id, sc)) {
> scan_balance = SCAN_FILE;
> goto out;
> }
> @@ -2653,7 +2670,7 @@ static void shrink_lruvec(struct lruvec
> * rebalance the anon lru active/inactive ratio.
> */
> if (can_reclaim_anon_pages(lruvec_memcg(lruvec),
> - lruvec_pgdat(lruvec)->node_id) &&
> + lruvec_pgdat(lruvec)->node_id, sc) &&
> inactive_is_low(lruvec, LRU_INACTIVE_ANON))
> shrink_active_list(SWAP_CLUSTER_MAX, lruvec,
> sc, LRU_ACTIVE_ANON);
> @@ -2724,7 +2741,7 @@ static inline bool should_continue_recla
> */
> pages_for_compaction = compact_gap(sc->order);
> inactive_lru_pages = node_page_state(pgdat, NR_INACTIVE_FILE);
> - if (can_reclaim_anon_pages(NULL, pgdat->node_id))
> + if (can_reclaim_anon_pages(NULL, pgdat->node_id, sc))
> inactive_lru_pages += node_page_state(pgdat, NR_INACTIVE_ANON);
>
> return inactive_lru_pages > pages_for_compaction;
> @@ -3485,7 +3502,7 @@ static void age_active_anon(struct pglis
> struct mem_cgroup *memcg;
> struct lruvec *lruvec;
>
> - if (!can_reclaim_anon_pages(NULL, pgdat->node_id))
> + if (!can_reclaim_anon_pages(NULL, pgdat->node_id, sc))
> return;
>
> lruvec = mem_cgroup_lruvec(NULL, pgdat);
> _
Powered by blists - more mailing lists