linux-kernel - Re: [RFC][PATCH 3/9] soft limit update filter

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
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20090407090438.9646e90c.kamezawa.hiroyu@jp.fujitsu.com>
Date:	Tue, 7 Apr 2009 09:04:38 +0900
From:	KAMEZAWA Hiroyuki <kamezawa.hiroyu@...fujitsu.com>
To:	balbir@...ux.vnet.ibm.com
Cc:	"linux-mm@...ck.org" <linux-mm@...ck.org>,
	"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
	"kosaki.motohiro@...fujitsu.com" <kosaki.motohiro@...fujitsu.com>
Subject: Re: [RFC][PATCH 3/9] soft limit update filter

On Mon, 6 Apr 2009 15:13:51 +0530
Balbir Singh <balbir@...ux.vnet.ibm.com> wrote:

> * KAMEZAWA Hiroyuki <kamezawa.hiroyu@...fujitsu.com> [2009-04-03 17:12:02]:
> 
> > No changes from v1.
> > ==
> > From: KAMEZAWA Hiroyuki <kamezawa.hiroyu@...fujitsu.com>
> > 
> > Check/Update softlimit information at every charge is over-killing, so
> > we need some filter.
> > 
> > This patch tries to count events in the memcg and if events > threshold
> > tries to update memcg's soft limit status and reset event counter to 0.
> > 
> > Event counter is maintained by per-cpu which has been already used,
> > Then, no siginificant overhead(extra cache-miss etc..) in theory.
> > 
> > Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@...fujitsu.com>
> > ---
> > Index: mmotm-2.6.29-Mar23/mm/memcontrol.c
> > ===================================================================
> > --- mmotm-2.6.29-Mar23.orig/mm/memcontrol.c
> > +++ mmotm-2.6.29-Mar23/mm/memcontrol.c
> > @@ -66,6 +66,7 @@ enum mem_cgroup_stat_index {
> >  	MEM_CGROUP_STAT_PGPGIN_COUNT,	/* # of pages paged in */
> >  	MEM_CGROUP_STAT_PGPGOUT_COUNT,	/* # of pages paged out */
> > 
> > +	MEM_CGROUP_STAT_EVENTS,  /* sum of page-in/page-out for internal use */
> >  	MEM_CGROUP_STAT_NSTATS,
> >  };
> > 
> > @@ -105,6 +106,22 @@ static s64 mem_cgroup_local_usage(struct
> >  	return ret;
> >  }
> > 
> > +/* For intenal use of per-cpu event counting. */
> > +
> > +static inline void
> > +__mem_cgroup_stat_reset_safe(struct mem_cgroup_stat_cpu *stat,
> > +		enum mem_cgroup_stat_index idx)
> > +{
> > +	stat->count[idx] = 0;
> > +}
> 
> Why do we do this and why do we need a special event?
> 
2 points.

  1.  we do "reset" this counter.
  2.  We're counting page-in/page-out. I wonder I should counter others...

> > +
> > +static inline s64
> > +__mem_cgroup_stat_read_local(struct mem_cgroup_stat_cpu *stat,
> > +			    enum mem_cgroup_stat_index idx)
> > +{
> > +	return stat->count[idx];
> > +}
> > +
> >  /*
> >   * per-zone information in memory controller.
> >   */
> > @@ -235,6 +252,8 @@ static void mem_cgroup_charge_statistics
> >  	else
> >  		__mem_cgroup_stat_add_safe(cpustat,
> >  				MEM_CGROUP_STAT_PGPGOUT_COUNT, 1);
> > +	__mem_cgroup_stat_add_safe(cpustat, MEM_CGROUP_STAT_EVENTS, 1);
> > +
> >  	put_cpu();
> >  }
> > 
> > @@ -897,9 +916,26 @@ static void record_last_oom(struct mem_c
> >  	mem_cgroup_walk_tree(mem, NULL, record_last_oom_cb);
> >  }
> > 
> > +#define SOFTLIMIT_EVENTS_THRESH (1024) /* 1024 times of page-in/out */
> > +/*
> > + * Returns true if sum of page-in/page-out events since last check is
> > + * over SOFTLIMIT_EVENT_THRESH. (counter is per-cpu.)
> > + */
> >  static bool mem_cgroup_soft_limit_check(struct mem_cgroup *mem)
> >  {
> > -	return false;
> > +	bool ret = false;
> > +	int cpu = get_cpu();
> > +	s64 val;
> > +	struct mem_cgroup_stat_cpu *cpustat;
> > +
> > +	cpustat = &mem->stat.cpustat[cpu];
> > +	val = __mem_cgroup_stat_read_local(cpustat, MEM_CGROUP_STAT_EVENTS);
> > +	if (unlikely(val > SOFTLIMIT_EVENTS_THRESH)) {
> > +		__mem_cgroup_stat_reset_safe(cpustat, MEM_CGROUP_STAT_EVENTS);
> > +		ret = true;
> > +	}
> > +	put_cpu();
> > +	return ret;
> >  }
> >
> 
> It is good to have the caller and the function in the same patch.
> Otherwise, you'll notice unused warnings. I think this function can be
> simplified further
> 
> 1. Lets gid rid of MEM_CGRUP_STAT_EVENTS
> 2. Lets rewrite mem_cgroup_soft_limit_check as
> 
> static bool mem_cgroup_soft_limit_check(struct mem_cgroup *mem)
> {
>      bool ret = false;
>      int cpu = get_cpu();
>      s64 pgin, pgout;
>      struct mem_cgroup_stat_cpu *cpustat;
> 
>      cpustat = &mem->stat.cpustat[cpu];
>      pgin = __mem_cgroup_stat_read_local(cpustat, MEM_CGROUP_STAT_PGPGIN_COUNT);
>      pgout = __mem_cgroup_stat_read_local(cpustat, MEM_CGROUP_STAT_PGPGOUT_COUNT);
>      val = pgin + pgout - mem->last_event_count;
>      if (unlikely(val > SOFTLIMIT_EVENTS_THRESH)) {
>              mem->last_event_count = pgin + pgout;
>              ret = true;
>      }
>      put_cpu();
>      return ret;
> }
> 
> mem->last_event_count can either be atomic or protected using one of
> the locks you intend to introduce. This will avoid the overhead of
> incrementing event at every charge_statistics.
> 
Incrementing always hits cache.

Hmm, making mem->last_event_count as per-cpu, we can do above. And maybe no
difference with current code. But you don't seem to like counting,
it's ok to change the shape.


Thanks,
-Kame


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/