linux-kernel - Re: [RFC][PATCH 4/5] memcg: per-cpu charge stock

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 for Android: free password hash cracker in your pocket

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20090831111027.GI4770@balbir.in.ibm.com>
Date:	Mon, 31 Aug 2009 16:40:27 +0530
From:	Balbir Singh <balbir@...ux.vnet.ibm.com>
To:	KAMEZAWA Hiroyuki <kamezawa.hiroyu@...fujitsu.com>
Cc:	"linux-mm@...ck.org" <linux-mm@...ck.org>,
	"linux-kernel@...r.kernel.org" <linux-kernel@...r.kernel.org>,
	"nishimura@....nes.nec.co.jp" <nishimura@....nes.nec.co.jp>
Subject: Re: [RFC][PATCH 4/5] memcg: per-cpu charge stock

* KAMEZAWA Hiroyuki <kamezawa.hiroyu@...fujitsu.com> [2009-08-28 13:27:06]:

> 
> For avoiding frequent access to res_counter at charge, add per-cpu
> local charge. Comparing with modifing res_coutner (with percpu_counter),
> this approach
> Pros.
> 	- we don't have to touch res_counter's cache line
> 	- we don't have to chase res_counter's hierarchy
> 	- we don't have to call res_counter function.
> Cons.
> 	- we need our own code.
> 
> Considering trade-off, I think this is worth to do.

I prefer the other part due to

1. Code reuse (any enhancements made will benefit us)
2. Custom batching that can be done easily
3. Remember hierarchy is explicitly enabled and we've documented that
it is expensive



>
> Signed-off-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@...fujitsu.com>
> ---
>  mm/memcontrol.c |   46 +++++++++++++++++++++++++++++++++++++---------
>  1 file changed, 37 insertions(+), 9 deletions(-)
> 
> Index: mmotm-2.6.31-Aug27/mm/memcontrol.c
> ===================================================================
> --- mmotm-2.6.31-Aug27.orig/mm/memcontrol.c
> +++ mmotm-2.6.31-Aug27/mm/memcontrol.c
> @@ -71,7 +71,7 @@ enum mem_cgroup_stat_index {
>  	MEM_CGROUP_STAT_PGPGOUT_COUNT,	/* # of pages paged out */
>  	MEM_CGROUP_STAT_EVENTS,	/* sum of pagein + pageout for internal use */
>  	MEM_CGROUP_STAT_SWAPOUT, /* # of pages, swapped out */
> -
> +	MEM_CGROUP_STAT_STOCK, /* # of private charges pre-allocated */
>  	MEM_CGROUP_STAT_NSTATS,
>  };
> 
> @@ -1266,6 +1266,32 @@ done:
>  	unlock_page_cgroup(pc);
>  }
> 
> +#define CHARGE_SIZE	(4 * ((NR_CPUS >> 5) + 1) * PAGE_SIZE)
> +
> +bool consume_local_stock(struct mem_cgroup *mem)
> +{
> +	struct mem_cgroup_stat_cpu *cstat;
> +	int cpu = get_cpu();
> +	bool ret = true;
> +
> +	cstat = &mem->stat.cpustat[cpu];
> +	if (cstat->count[MEM_CGROUP_STAT_STOCK])
> +		cstat->count[MEM_CGROUP_STAT_STOCK] -= PAGE_SIZE;
> +	else
> +		ret = false;
> +	put_cpu();
> +	return ret;
> +}
> +
> +void do_local_stock(struct mem_cgroup *mem, int val)
> +{
> +	struct mem_cgroup_stat_cpu *cstat;
> +	int cpu = get_cpu();
> +	cstat = &mem->stat.cpustat[cpu];
> +	__mem_cgroup_stat_add_safe(cstat, MEM_CGROUP_STAT_STOCK, val);
> +	put_cpu();
> +}
> +
>  /*
>   * Unlike exported interface, "oom" parameter is added. if oom==true,
>   * oom-killer can be invoked.
> @@ -1297,28 +1323,30 @@ static int __mem_cgroup_try_charge(struc
>  	} else {
>  		css_get(&mem->css);
>  	}
> -	if (unlikely(!mem))
> +	/* css_get() against root cgroup is NOOP. we can ignore it */
> +	if (!mem || mem_cgroup_is_root(mem))
>  		return 0;
> 
>  	VM_BUG_ON(css_is_removed(&mem->css));
> 
> +	if (consume_local_stock(mem))
> +		goto got;
> +
>  	while (1) {
>  		int ret = 0;
>  		unsigned long flags = 0;
> 
> -		if (mem_cgroup_is_root(mem))
> -			goto done;
> -		ret = res_counter_charge(&mem->res, PAGE_SIZE, &fail_res);
> +		ret = res_counter_charge(&mem->res, CHARGE_SIZE, &fail_res);
> 
>  		if (likely(!ret)) {
>  			if (!do_swap_account)
>  				break;
> -			ret = res_counter_charge(&mem->memsw, PAGE_SIZE,
> +			ret = res_counter_charge(&mem->memsw, CHARGE_SIZE,
>  						&fail_res);
>  			if (likely(!ret))
>  				break;
>  			/* mem+swap counter fails */
> -			res_counter_uncharge(&mem->res, PAGE_SIZE);
> +			res_counter_uncharge(&mem->res, CHARGE_SIZE);
>  			flags |= MEM_CGROUP_RECLAIM_NOSWAP;
>  			mem_over_limit = mem_cgroup_from_res_counter(fail_res,
>  									memsw);
> @@ -1356,7 +1384,8 @@ static int __mem_cgroup_try_charge(struc
>  			goto nomem;
>  		}
>  	}
> -
> +	do_local_stock(mem, CHARGE_SIZE - PAGE_SIZE);
> +got:
>  	/*
>  	 * check hierarchy root's event counter and modify softlimit-tree
>  	 * if necessary.
> @@ -1364,7 +1393,6 @@ static int __mem_cgroup_try_charge(struc
>  	mem_over_soft_limit = mem_cgroup_soft_limit_check(mem);
>  	if (mem_over_soft_limit)
>  		mem_cgroup_update_tree(mem_over_soft_limit, page);
> -done:
>  	return 0;
>  nomem:
>  	css_put(&mem->css);
> 

-- 
	Balbir
--
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/