| 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: <CAJD7tkaGWqX1azMfVo_RnteNHmSfkOMhoSKbns5jeSf+Ju6g=A@mail.gmail.com>
Date: Tue, 25 Jul 2023 16:58:48 -0700
From: Yosry Ahmed <yosryahmed@...gle.com>
To: Johannes Weiner <hannes@...xchg.org>,
Michal Hocko <mhocko@...nel.org>,
Roman Gushchin <roman.gushchin@...ux.dev>,
Shakeel Butt <shakeelb@...gle.com>,
Muchun Song <muchun.song@...ux.dev>,
Andrew Morton <akpm@...ux-foundation.org>
Cc: linux-kernel@...r.kernel.org, cgroups@...r.kernel.org,
linux-mm@...ck.org
Subject: Re: [PATCH] mm: memcg: use rstat for non-hierarchical stats
On Wed, Jul 19, 2023 at 10:46 AM Yosry Ahmed <yosryahmed@...gle.com> wrote:
>
> Currently, memcg uses rstat to maintain hierarchical stats. The rstat
> framework keeps track of which cgroups have updates on which cpus.
>
> For non-hierarchical stats, as memcg moved to rstat, they are no longer
> readily available as counters. Instead, the percpu counters for a given
> stat need to be summed to get the non-hierarchical stat value. This
> causes a performance regression when reading non-hierarchical stats on
> kernels where memcg moved to using rstat. This is especially visible
> when reading memory.stat on cgroup v1. There are also some code paths
> internal to the kernel that read such non-hierarchical stats.
>
> It is inefficient to iterate and sum counters in all cpus when the rstat
> framework knows exactly when a percpu counter has an update. Instead,
> maintain cpu-aggregated non-hierarchical counters for each stat. During
> an rstat flush, keep those updated as well. When reading
> non-hierarchical stats, we no longer need to iterate cpus, we just need
> to read the maintainer counters, similar to hierarchical stats.
>
> A caveat is that we now a stats flush before reading
> local/non-hierarchical stats through {memcg/lruvec}_page_state_local()
> or memcg_events_local(), where we previously only needed a flush to
> read hierarchical stats. Most contexts reading non-hierarchical stats
> are already doing a flush, add a flush to the only missing context in
> count_shadow_nodes().
>
> With this patch, reading memory.stat from 1000 memcgs is 3x faster on a
> machine with 256 cpus on cgroup v1:
> # for i in $(seq 1000); do mkdir /sys/fs/cgroup/memory/cg$i; done
> # time cat /dev/cgroup/memory/cg*/memory.stat > /dev/null
> real 0m0.125s
> user 0m0.005s
> sys 0m0.120s
>
> After:
> real 0m0.032s
> user 0m0.005s
> sys 0m0.027s
>
> Signed-off-by: Yosry Ahmed <yosryahmed@...gle.com>
> ---
> include/linux/memcontrol.h | 7 ++++---
> mm/memcontrol.c | 32 +++++++++++++++++++-------------
> mm/workingset.c | 1 +
> 3 files changed, 24 insertions(+), 16 deletions(-)
>
> diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
> index 5818af8eca5a..a9f2861a57a5 100644
> --- a/include/linux/memcontrol.h
> +++ b/include/linux/memcontrol.h
> @@ -112,6 +112,9 @@ struct lruvec_stats {
> /* Aggregated (CPU and subtree) state */
> long state[NR_VM_NODE_STAT_ITEMS];
>
> + /* Non-hierarchical (CPU aggregated) state */
> + long state_local[NR_VM_NODE_STAT_ITEMS];
> +
> /* Pending child counts during tree propagation */
> long state_pending[NR_VM_NODE_STAT_ITEMS];
> };
> @@ -1020,14 +1023,12 @@ static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec,
> {
> struct mem_cgroup_per_node *pn;
> long x = 0;
> - int cpu;
>
> if (mem_cgroup_disabled())
> return node_page_state(lruvec_pgdat(lruvec), idx);
>
> pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec);
> - for_each_possible_cpu(cpu)
> - x += per_cpu(pn->lruvec_stats_percpu->state[idx], cpu);
> + x = READ_ONCE(pn->lruvec_stats.state_local[idx]);
> #ifdef CONFIG_SMP
> if (x < 0)
> x = 0;
> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> index e8ca4bdcb03c..90a22637818e 100644
> --- a/mm/memcontrol.c
> +++ b/mm/memcontrol.c
> @@ -742,6 +742,10 @@ struct memcg_vmstats {
> long state[MEMCG_NR_STAT];
> unsigned long events[NR_MEMCG_EVENTS];
>
> + /* Non-hierarchical (CPU aggregated) page state & events */
> + long state_local[MEMCG_NR_STAT];
> + unsigned long events_local[NR_MEMCG_EVENTS];
> +
> /* Pending child counts during tree propagation */
> long state_pending[MEMCG_NR_STAT];
> unsigned long events_pending[NR_MEMCG_EVENTS];
> @@ -775,11 +779,8 @@ void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int val)
> /* idx can be of type enum memcg_stat_item or node_stat_item. */
> static unsigned long memcg_page_state_local(struct mem_cgroup *memcg, int idx)
> {
> - long x = 0;
> - int cpu;
> + long x = READ_ONCE(memcg->vmstats->state_local[idx]);
>
> - for_each_possible_cpu(cpu)
> - x += per_cpu(memcg->vmstats_percpu->state[idx], cpu);
> #ifdef CONFIG_SMP
> if (x < 0)
> x = 0;
> @@ -926,16 +927,12 @@ static unsigned long memcg_events(struct mem_cgroup *memcg, int event)
>
> static unsigned long memcg_events_local(struct mem_cgroup *memcg, int event)
> {
> - long x = 0;
> - int cpu;
> int index = memcg_events_index(event);
>
> if (index < 0)
> return 0;
>
> - for_each_possible_cpu(cpu)
> - x += per_cpu(memcg->vmstats_percpu->events[index], cpu);
> - return x;
> + return READ_ONCE(memcg->vmstats->events_local[index]);
> }
>
> static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg,
> @@ -5526,7 +5523,7 @@ static void mem_cgroup_css_rstat_flush(struct cgroup_subsys_state *css, int cpu)
> struct mem_cgroup *memcg = mem_cgroup_from_css(css);
> struct mem_cgroup *parent = parent_mem_cgroup(memcg);
> struct memcg_vmstats_percpu *statc;
> - long delta, v;
> + long delta, delta_cpu, v;
> int i, nid;
>
> statc = per_cpu_ptr(memcg->vmstats_percpu, cpu);
> @@ -5542,9 +5539,11 @@ static void mem_cgroup_css_rstat_flush(struct cgroup_subsys_state *css, int cpu)
> memcg->vmstats->state_pending[i] = 0;
>
> /* Add CPU changes on this level since the last flush */
> + delta_cpu = 0;
> v = READ_ONCE(statc->state[i]);
> if (v != statc->state_prev[i]) {
> - delta += v - statc->state_prev[i];
> + delta_cpu = v - statc->state_prev[i];
> + delta += delta_cpu;
> statc->state_prev[i] = v;
> }
>
> @@ -5553,6 +5552,7 @@ static void mem_cgroup_css_rstat_flush(struct cgroup_subsys_state *css, int cpu)
>
> /* Aggregate counts on this level and propagate upwards */
> memcg->vmstats->state[i] += delta;
> + memcg->vmstats->state_local[i] += delta_cpu;
I ran this through more testing. There is a subtle problem here. If
delta == 0 and delta_cpu != 0, we will skip the update to the local
stats. This happens in the very unlikely case where the delta on the
flushed cpu is equal in value but of opposite sign to the delta coming
from the children. IOW if (statc->state[i] - statc->state_prev[i]) ==
-memcg->vmstats->state_pending[i].
Very unlikely but I happened to stumble upon it. Will fix this for v2.
> if (parent)
> parent->vmstats->state_pending[i] += delta;
> }
> @@ -5562,9 +5562,11 @@ static void mem_cgroup_css_rstat_flush(struct cgroup_subsys_state *css, int cpu)
> if (delta)
> memcg->vmstats->events_pending[i] = 0;
>
> + delta_cpu = 0;
> v = READ_ONCE(statc->events[i]);
> if (v != statc->events_prev[i]) {
> - delta += v - statc->events_prev[i];
> + delta_cpu = v - statc->events_prev[i];
> + delta += delta_cpu;
> statc->events_prev[i] = v;
> }
>
> @@ -5572,6 +5574,7 @@ static void mem_cgroup_css_rstat_flush(struct cgroup_subsys_state *css, int cpu)
> continue;
>
> memcg->vmstats->events[i] += delta;
> + memcg->vmstats->events_local[i] += delta_cpu;
> if (parent)
> parent->vmstats->events_pending[i] += delta;
> }
> @@ -5591,9 +5594,11 @@ static void mem_cgroup_css_rstat_flush(struct cgroup_subsys_state *css, int cpu)
> if (delta)
> pn->lruvec_stats.state_pending[i] = 0;
>
> + delta_cpu = 0;
> v = READ_ONCE(lstatc->state[i]);
> if (v != lstatc->state_prev[i]) {
> - delta += v - lstatc->state_prev[i];
> + delta_cpu = v - lstatc->state_prev[i];
> + delta += delta_cpu;
> lstatc->state_prev[i] = v;
> }
>
> @@ -5601,6 +5606,7 @@ static void mem_cgroup_css_rstat_flush(struct cgroup_subsys_state *css, int cpu)
> continue;
>
> pn->lruvec_stats.state[i] += delta;
> + pn->lruvec_stats.state_local[i] += delta_cpu;
> if (ppn)
> ppn->lruvec_stats.state_pending[i] += delta;
> }
> diff --git a/mm/workingset.c b/mm/workingset.c
> index 4686ae363000..da58a26d0d4d 100644
> --- a/mm/workingset.c
> +++ b/mm/workingset.c
> @@ -664,6 +664,7 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker,
> struct lruvec *lruvec;
> int i;
>
> + mem_cgroup_flush_stats();
> lruvec = mem_cgroup_lruvec(sc->memcg, NODE_DATA(sc->nid));
> for (pages = 0, i = 0; i < NR_LRU_LISTS; i++)
> pages += lruvec_page_state_local(lruvec,
> --
> 2.41.0.255.g8b1d071c50-goog
>
Powered by blists - more mailing lists