Linux Container Development
 help / color / mirror / Atom feed
From: yamamoto-jCdQPDEk3idL9jVzuh4AOg@public.gmane.org (YAMAMOTO Takashi)
To: kamezawa.hiroyu-+CUm20s59erQFUHtdCDX3A@public.gmane.org
Cc: containers-qjLDD68F18O7TbgM5vRIOg@public.gmane.org,
	balbir-23VcF4HTsmIX0ybBhKVfKdBPR1lH4CV8@public.gmane.org,
	xemul-GEFAQzZX7r8dnm+yROfE0A@public.gmane.org
Subject: Re: [RFC] memory controller : backgorund reclaim and avoid excessive locking [5/5] lazy page_cgroup freeing
Date: Mon, 18 Feb 2008 10:58:40 +0900 (JST)	[thread overview]
Message-ID: <20080218015840.CE6FF1E3C58@siro.lan> (raw)
In-Reply-To: Your message of "Thu, 14 Feb 2008 17:36:24 +0900" <20080214173624.d29b26d9.kamezawa.hiroyu-+CUm20s59erQFUHtdCDX3A@public.gmane.org>

> +	/*
> +	 * For lazy freeing (not GC)
> +	 */
> +	struct {
> +		struct mem_cgroup_per_zone *mz;
> +		int			num;
> +#define GARBAGE_MAXSIZE		(16)
> +		struct page_cgroup	*vec[GARBAGE_MAXSIZE];
> +	} garbage[NR_CPUS];
>  };

i think you want to dedicate cache lines.

> @@ -176,12 +185,14 @@ struct page_cgroup {
>  	struct list_head lru;		/* per cgroup LRU list */
>  	struct page *page;
>  	struct mem_cgroup *mem_cgroup;
> +	struct mem_cgroup_per_zone *mz;	/* now belongs to...*/

is this for performance?

> @@ -408,10 +427,12 @@ static void __mem_cgroup_move_lists(stru
>  	if (active) {
>  		MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_ACTIVE) += 1;
>  		pc->flags |= PAGE_CGROUP_FLAG_ACTIVE;
> +		pc->mz = mz;
>  		list_move(&pc->lru, &mz->active_list);
>  	} else {
>  		MEM_CGROUP_ZSTAT(mz, MEM_CGROUP_ZSTAT_INACTIVE) += 1;
>  		pc->flags &= ~PAGE_CGROUP_FLAG_ACTIVE;
> +		pc->mz = mz;
>  		list_move(&pc->lru, &mz->inactive_list);
>  	}
>  }

isn't pc->mz already assigned by __mem_cgroup_add_list?

> @@ -1050,11 +1114,15 @@ mem_cgroup_force_empty_list(struct mem_c
>  	if (list_empty(list))
>  		return;
>  retry:
> +	all_free_garbages(mem);
>  	count = FORCE_UNCHARGE_BATCH;
>  	spin_lock_irqsave(&mz->lru_lock, flags);
>  
>  	while (--count && !list_empty(list)) {
>  		pc = list_entry(list->prev, struct page_cgroup, lru);
> +		/* If there are still garbage, exit and retry */
> +		if (pc->flags & PAGE_CGROUP_FLAG_GARBAGE)
> +			break;

i think mem_cgroup_isolate_pages needs a similar check.

YAMAMOTO Takashi

  parent reply	other threads:[~2008-02-18  1:58 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-02-14  8:21 [RFC] memory controller : backgorund reclaim and avoid excessive locking [0/5] KAMEZAWA Hiroyuki
     [not found] ` <20080214172148.bfd564d5.kamezawa.hiroyu-+CUm20s59erQFUHtdCDX3A@public.gmane.org>
2008-02-14  8:28   ` [RFC] memory controller : backgorund reclaim and avoid excessive locking [1/5] high-low watermark KAMEZAWA Hiroyuki
     [not found]     ` <20080214172801.b1c35067.kamezawa.hiroyu-+CUm20s59erQFUHtdCDX3A@public.gmane.org>
2008-02-14  8:48       ` Balbir Singh
     [not found]         ` <47B40061.20200-23VcF4HTsmIX0ybBhKVfKdBPR1lH4CV8@public.gmane.org>
2008-02-14  9:12           ` KAMEZAWA Hiroyuki
2008-02-14  8:29   ` [RFC] memory controller : backgorund reclaim and avoid excessive locking [2/5] background reclaim KAMEZAWA Hiroyuki
     [not found]     ` <20080214172910.017cc755.kamezawa.hiroyu-+CUm20s59erQFUHtdCDX3A@public.gmane.org>
2008-02-14  8:32       ` Balbir Singh
     [not found]         ` <47B3FCAC.6010109-23VcF4HTsmIX0ybBhKVfKdBPR1lH4CV8@public.gmane.org>
2008-02-14  8:57           ` KAMEZAWA Hiroyuki
2008-02-14  8:30   ` [RFC] memory controller : backgorund reclaim and avoid excessive locking [3/5] throttling KAMEZAWA Hiroyuki
     [not found]     ` <20080214173043.d57b3619.kamezawa.hiroyu-+CUm20s59erQFUHtdCDX3A@public.gmane.org>
2008-02-14  9:14       ` Balbir Singh
     [not found]         ` <47B4068A.2050104-23VcF4HTsmIX0ybBhKVfKdBPR1lH4CV8@public.gmane.org>
2008-02-14  9:38           ` KAMEZAWA Hiroyuki
2008-02-14  8:35   ` [RFC] memory controller : backgorund reclaim and avoid excessive locking [4/5] borrow resource KAMEZAWA Hiroyuki
     [not found]     ` <20080214173504.cc1aa42e.kamezawa.hiroyu-+CUm20s59erQFUHtdCDX3A@public.gmane.org>
2008-02-18  0:53       ` YAMAMOTO Takashi
     [not found]         ` <20080218005335.D93F51E3C5A-Pcsii4f/SVk@public.gmane.org>
2008-02-18  2:06           ` KAMEZAWA Hiroyuki
2008-02-14  8:36   ` [RFC] memory controller : backgorund reclaim and avoid excessive locking [5/5] lazy page_cgroup freeing KAMEZAWA Hiroyuki
     [not found]     ` <20080214173624.d29b26d9.kamezawa.hiroyu-+CUm20s59erQFUHtdCDX3A@public.gmane.org>
2008-02-18  1:58       ` YAMAMOTO Takashi [this message]
     [not found]         ` <20080218015840.CE6FF1E3C58-Pcsii4f/SVk@public.gmane.org>
2008-02-18  2:11           ` KAMEZAWA Hiroyuki
2008-02-18  4:35       ` Balbir Singh
     [not found]         ` <47B90B04.3090001-23VcF4HTsmIX0ybBhKVfKdBPR1lH4CV8@public.gmane.org>
2008-02-18  4:55           ` KAMEZAWA Hiroyuki

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=20080218015840.CE6FF1E3C58@siro.lan \
    --to=yamamoto-jcdqpdek3idl9jvzuh4aog@public.gmane.org \
    --cc=balbir-23VcF4HTsmIX0ybBhKVfKdBPR1lH4CV8@public.gmane.org \
    --cc=containers-qjLDD68F18O7TbgM5vRIOg@public.gmane.org \
    --cc=kamezawa.hiroyu-+CUm20s59erQFUHtdCDX3A@public.gmane.org \
    --cc=xemul-GEFAQzZX7r8dnm+yROfE0A@public.gmane.org \
    /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