linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Glauber Costa <glommer@parallels.com>
To: Suleiman Souhlal <ssouhlal@FreeBSD.org>
Cc: cgroups@vger.kernel.org, suleiman@google.com,
	kamezawa.hiroyu@jp.fujitsu.com, penberg@kernel.org,
	yinghan@google.com, hughd@google.com, gthelen@google.com,
	linux-mm@kvack.org, devel@openvz.org
Subject: Re: [PATCH 01/10] memcg: Kernel memory accounting infrastructure.
Date: Tue, 28 Feb 2012 10:10:09 -0300	[thread overview]
Message-ID: <4F4CD231.907@parallels.com> (raw)
In-Reply-To: <1330383533-20711-2-git-send-email-ssouhlal@FreeBSD.org>

On 02/27/2012 07:58 PM, Suleiman Souhlal wrote:
> Enabled with CONFIG_CGROUP_MEM_RES_CTLR_KMEM.
>
> Adds the following files:
>      - memory.kmem.independent_kmem_limit
>      - memory.kmem.usage_in_bytes
>      - memory.kmem.limit_in_bytes
>
> Signed-off-by: Suleiman Souhlal<suleiman@google.com>
> ---
>   mm/memcontrol.c |  121 ++++++++++++++++++++++++++++++++++++++++++++++++++++++-
>   1 files changed, 120 insertions(+), 1 deletions(-)
>
> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> index 228d646..11e31d6 100644
> --- a/mm/memcontrol.c
> +++ b/mm/memcontrol.c
> @@ -235,6 +235,10 @@ struct mem_cgroup {
>   	 */
>   	struct res_counter memsw;
>   	/*
> +	 * the counter to account for kernel memory usage.
> +	 */
> +	struct res_counter kmem_bytes;
> +	/*
Not terribly important, but I find this name inconsistent. I like
just kmem better.

>   	 * Per cgroup active and inactive list, similar to the
>   	 * per zone LRU lists.
>   	 */
> @@ -293,6 +297,7 @@ struct mem_cgroup {
>   #ifdef CONFIG_INET
>   	struct tcp_memcontrol tcp_mem;
>   #endif
> +	int independent_kmem_limit;
>   };
bool ?

But that said, we are now approaching some 4 or 5 selectables in the 
memcg structure. How about we turn them into flags?

>   /* Stuffs for move charges at task migration. */
> @@ -354,6 +359,7 @@ enum charge_type {
>   #define _MEM			(0)
>   #define _MEMSWAP		(1)
>   #define _OOM_TYPE		(2)
> +#define _KMEM			(3)
>   #define MEMFILE_PRIVATE(x, val)	(((x)<<  16) | (val))
>   #define MEMFILE_TYPE(val)	(((val)>>  16)&  0xffff)
>   #define MEMFILE_ATTR(val)	((val)&  0xffff)
> @@ -370,6 +376,8 @@ enum charge_type {
>
>   static void mem_cgroup_get(struct mem_cgroup *memcg);
>   static void mem_cgroup_put(struct mem_cgroup *memcg);
> +static void memcg_kmem_init(struct mem_cgroup *memcg,
> +    struct mem_cgroup *parent);
>
>   /* Writing them here to avoid exposing memcg's inner layout */
>   #ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
> @@ -1402,6 +1410,10 @@ done:
>   		res_counter_read_u64(&memcg->memsw, RES_USAGE)>>  10,
>   		res_counter_read_u64(&memcg->memsw, RES_LIMIT)>>  10,
>   		res_counter_read_u64(&memcg->memsw, RES_FAILCNT));
> +	printk(KERN_INFO "kmem: usage %llukB, limit %llukB, failcnt %llu\n",
> +		res_counter_read_u64(&memcg->kmem_bytes, RES_USAGE)>>  10,
> +		res_counter_read_u64(&memcg->kmem_bytes, RES_LIMIT)>>  10,
> +		res_counter_read_u64(&memcg->kmem_bytes, RES_FAILCNT));
>   }
>
>   /*
> @@ -3840,6 +3852,9 @@ static u64 mem_cgroup_read(struct cgroup *cont, struct cftype *cft)
>   		else
>   			val = res_counter_read_u64(&memcg->memsw, name);
>   		break;
> +	case _KMEM:
> +		val = res_counter_read_u64(&memcg->kmem_bytes, name);
> +		break;
>   	default:
>   		BUG();
>   		break;
> @@ -3872,8 +3887,14 @@ static int mem_cgroup_write(struct cgroup *cont, struct cftype *cft,
>   			break;
>   		if (type == _MEM)
>   			ret = mem_cgroup_resize_limit(memcg, val);
> -		else
> +		else if (type == _MEMSWAP)
>   			ret = mem_cgroup_resize_memsw_limit(memcg, val);
> +		else if (type == _KMEM) {
> +			if (!memcg->independent_kmem_limit)
> +				return -EINVAL;
> +			ret = res_counter_set_limit(&memcg->kmem_bytes, val);
> +		} else
> +			return -EINVAL;
>   		break;
>   	case RES_SOFT_LIMIT:
>   		ret = res_counter_memparse_write_strategy(buffer,&val);
> @@ -4572,8 +4593,47 @@ static int mem_control_numa_stat_open(struct inode *unused, struct file *file)
>   #endif /* CONFIG_NUMA */
>
>   #ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
> +static u64
> +mem_cgroup_independent_kmem_limit_read(struct cgroup *cgrp, struct cftype *cft)
> +{
> +	return mem_cgroup_from_cont(cgrp)->independent_kmem_limit;
> +}
> +
> +static int mem_cgroup_independent_kmem_limit_write(struct cgroup *cgrp,
> +    struct cftype *cft, u64 val)
> +{
> +	mem_cgroup_from_cont(cgrp)->independent_kmem_limit = !!val;
> +
> +	return 0;
> +}
> +
> +static struct cftype kmem_cgroup_files[] = {
> +	{
> +		.name = "kmem.independent_kmem_limit",
> +		.write_u64 = mem_cgroup_independent_kmem_limit_write,
> +		.read_u64 = mem_cgroup_independent_kmem_limit_read,
> +	},
> +	{
> +		.name = "kmem.limit_in_bytes",
> +		.private = MEMFILE_PRIVATE(_KMEM, RES_LIMIT),
> +		.write_string = mem_cgroup_write,
> +		.read_u64 = mem_cgroup_read,
> +	},
> +	{
> +		.name = "kmem.usage_in_bytes",
> +		.private = MEMFILE_PRIVATE(_KMEM, RES_USAGE),
> +		.read_u64 = mem_cgroup_read,
> +	},
> +};
> +
>   static int register_kmem_files(struct cgroup *cont, struct cgroup_subsys *ss)
>   {
> +	int ret;
> +
> +	ret = cgroup_add_files(cont, ss, kmem_cgroup_files,
> +	    ARRAY_SIZE(kmem_cgroup_files));
> +	if (ret)
> +		return ret;
>   	/*
>   	 * Part of this would be better living in a separate allocation
>   	 * function, leaving us with just the cgroup tree population work.
> @@ -4587,6 +4647,10 @@ static int register_kmem_files(struct cgroup *cont, struct cgroup_subsys *ss)
>   static void kmem_cgroup_destroy(struct cgroup_subsys *ss,
>   				struct cgroup *cont)
>   {
> +	struct mem_cgroup *memcg;
> +
> +	memcg = mem_cgroup_from_cont(cont);
> +	BUG_ON(res_counter_read_u64(&memcg->kmem_bytes, RES_USAGE) != 0);
That does not seem to make sense, specially if you are doing lazy 
creation. What happens if you create a cgroup, don't put any tasks into 
it (therefore, usage == 0), and then destroy it right away?

Or am I missing something?

>   	mem_cgroup_sockets_destroy(cont, ss);
>   }
>   #else
> @@ -4938,6 +5002,7 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
>   	}
>   	memcg->last_scanned_node = MAX_NUMNODES;
>   	INIT_LIST_HEAD(&memcg->oom_notify);
> +	memcg_kmem_init(memcg, parent&&  parent->use_hierarchy ? parent : NULL);
>
>   	if (parent)
>   		memcg->swappiness = mem_cgroup_swappiness(parent);
> @@ -5519,3 +5584,57 @@ static int __init enable_swap_account(char *s)
>   __setup("swapaccount=", enable_swap_account);
>
>   #endif
> +
> +#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM
> +int
> +memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, long long delta)
> +{
> +	struct res_counter *fail_res;
> +	struct mem_cgroup *_memcg;
> +	int may_oom, ret;
> +
> +	may_oom = (gfp&  __GFP_WAIT)&&  (gfp&  __GFP_FS)&&
> +	    !(gfp&  __GFP_NORETRY);
> +
> +	ret = 0;
> +
> +	if (memcg&&  !memcg->independent_kmem_limit) {
> +		_memcg = memcg;
> +		if (__mem_cgroup_try_charge(NULL, gfp, delta / PAGE_SIZE,
> +		&_memcg, may_oom) != 0)
> +			return -ENOMEM;
> +	}
> +
> +	if (_memcg)
> +		ret = res_counter_charge(&_memcg->kmem_bytes, delta,&fail_res);
> +
> +	return ret;
> +}
> +
> +void
> +memcg_uncharge_kmem(struct mem_cgroup *memcg, long long delta)
> +{
> +	if (memcg)
> +		res_counter_uncharge(&memcg->kmem_bytes, delta);
> +
> +	if (memcg&&  !memcg->independent_kmem_limit)
> +		res_counter_uncharge(&memcg->res, delta);
> +}
> +
> +static void
> +memcg_kmem_init(struct mem_cgroup *memcg, struct mem_cgroup *parent)
> +{
> +	struct res_counter *parent_res;
> +
> +	parent_res = NULL;
> +	if (parent&&  parent != root_mem_cgroup)
> +		parent_res =&parent->kmem_bytes;
> +	res_counter_init(&memcg->kmem_bytes, parent_res);
> +	memcg->independent_kmem_limit = 0;
> +}
> +#else /* CONFIG_CGROUP_MEM_RES_CTLR_KMEM */
> +static void
> +memcg_kmem_init(struct mem_cgroup *memcg, struct mem_cgroup *parent)
> +{
> +}
> +#endif /* CONFIG_CGROUP_MEM_RES_CTLR_KMEM */

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

  reply	other threads:[~2012-02-28 13:11 UTC|newest]

Thread overview: 52+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-02-27 22:58 [PATCH 00/10] memcg: Kernel Memory Accounting Suleiman Souhlal
2012-02-27 22:58 ` [PATCH 01/10] memcg: Kernel memory accounting infrastructure Suleiman Souhlal
2012-02-28 13:10   ` Glauber Costa [this message]
2012-02-29  0:37     ` Suleiman Souhlal
2012-02-28 13:11   ` Glauber Costa
2012-02-27 22:58 ` [PATCH 02/10] memcg: Uncharge all kmem when deleting a cgroup Suleiman Souhlal
2012-02-28 19:00   ` Glauber Costa
2012-02-29  0:24     ` Suleiman Souhlal
2012-02-29 16:51       ` Glauber Costa
2012-02-29  6:22   ` KAMEZAWA Hiroyuki
2012-02-29 19:00     ` Suleiman Souhlal
2012-02-27 22:58 ` [PATCH 03/10] memcg: Reclaim when more than one page needed Suleiman Souhlal
2012-02-29  6:18   ` KAMEZAWA Hiroyuki
2012-02-27 22:58 ` [PATCH 04/10] memcg: Introduce __GFP_NOACCOUNT Suleiman Souhlal
2012-02-29  6:00   ` KAMEZAWA Hiroyuki
2012-02-29 16:53     ` Glauber Costa
2012-02-29 19:09     ` Suleiman Souhlal
2012-03-01  0:10       ` KAMEZAWA Hiroyuki
2012-03-01  0:24         ` Glauber Costa
2012-03-01  6:05           ` KAMEZAWA Hiroyuki
2012-03-03 14:22             ` Glauber Costa
2012-03-03 16:38               ` Suleiman Souhlal
2012-03-03 23:24                 ` Glauber Costa
2012-03-04  0:10                   ` Suleiman Souhlal
2012-03-06 10:36                     ` Glauber Costa
2012-03-06 16:13                       ` Suleiman Souhlal
2012-03-06 18:31                         ` Glauber Costa
2012-02-27 22:58 ` [PATCH 05/10] memcg: Slab accounting Suleiman Souhlal
2012-02-28 13:24   ` Glauber Costa
2012-02-28 23:31     ` Suleiman Souhlal
2012-02-29 17:00       ` Glauber Costa
2012-02-27 22:58 ` [PATCH 06/10] memcg: Track all the memcg children of a kmem_cache Suleiman Souhlal
2012-02-27 22:58 ` [PATCH 07/10] memcg: Stop res_counter underflows Suleiman Souhlal
2012-02-28 13:31   ` Glauber Costa
2012-02-28 23:07     ` Suleiman Souhlal
2012-02-29 17:05       ` Glauber Costa
2012-02-29 19:17         ` Suleiman Souhlal
2012-02-27 22:58 ` [PATCH 08/10] memcg: Add CONFIG_CGROUP_MEM_RES_CTLR_KMEM_ACCT_ROOT Suleiman Souhlal
2012-02-28 13:34   ` Glauber Costa
2012-02-28 23:36     ` Suleiman Souhlal
2012-02-28 23:54       ` KAMEZAWA Hiroyuki
2012-02-29 17:09       ` Glauber Costa
2012-02-29 19:24         ` Suleiman Souhlal
2012-02-27 22:58 ` [PATCH 09/10] memcg: Per-memcg memory.kmem.slabinfo file Suleiman Souhlal
2012-02-27 22:58 ` [PATCH 10/10] memcg: Document kernel memory accounting Suleiman Souhlal
2012-02-27 23:05   ` Randy Dunlap
2012-02-28  8:49 ` [PATCH 00/10] memcg: Kernel Memory Accounting Pekka Enberg
2012-02-28 22:12   ` Suleiman Souhlal
2012-02-28 13:03 ` Glauber Costa
2012-02-28 22:47   ` Suleiman Souhlal
2012-02-29 16:47     ` Glauber Costa
2012-02-29 19:28       ` Suleiman Souhlal

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=4F4CD231.907@parallels.com \
    --to=glommer@parallels.com \
    --cc=cgroups@vger.kernel.org \
    --cc=devel@openvz.org \
    --cc=gthelen@google.com \
    --cc=hughd@google.com \
    --cc=kamezawa.hiroyu@jp.fujitsu.com \
    --cc=linux-mm@kvack.org \
    --cc=penberg@kernel.org \
    --cc=ssouhlal@FreeBSD.org \
    --cc=suleiman@google.com \
    --cc=yinghan@google.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).