From mboxrd@z Thu Jan 1 00:00:00 1970 From: Kamezawa Hiroyuki Subject: Re: [PATCH v2 2/5] memcg: provide root figures from system totals Date: Thu, 14 Mar 2013 09:03:15 +0900 Message-ID: <514113C3.2090505@jp.fujitsu.com> References: <1362489058-3455-1-git-send-email-glommer@parallels.com> <1362489058-3455-3-git-send-email-glommer@parallels.com> <51368D80.20701@jp.fujitsu.com> <5136FEC2.2050004@parallels.com> <51371E4A.7090807@jp.fujitsu.com> <51371FEF.3020507@parallels.com> <513721A5.6080401@jp.fujitsu.com> <514043B5.1090205@jp.fujitsu.com> Mime-Version: 1.0 Content-Transfer-Encoding: quoted-printable Return-path: In-Reply-To: Sender: owner-linux-mm@kvack.org List-ID: Content-Type: text/plain; charset="windows-1252"; format="flowed" To: Sha Zhengju Cc: Glauber Costa , linux-mm@kvack.org, cgroups@vger.kernel.org, Tejun Heo , Andrew Morton , Michal Hocko , anton.vorontsov@linaro.org, Johannes Weiner , Mel Gorman (2013/03/13 18:59), Sha Zhengju wrote: > On Wed, Mar 13, 2013 at 5:15 PM, Kamezawa Hiroyuki > wrote: >> (2013/03/13 15:58), Sha Zhengju wrote: >>> >>> On Wed, Mar 6, 2013 at 6:59 PM, Kamezawa Hiroyuki >>> wrote: >>>> >>>> (2013/03/06 19:52), Glauber Costa wrote: >>>>> >>>>> On 03/06/2013 02:45 PM, Kamezawa Hiroyuki wrote: >>>>>> >>>>>> (2013/03/06 17:30), Glauber Costa wrote: >>>>>>> >>>>>>> On 03/06/2013 04:27 AM, Kamezawa Hiroyuki wrote: >>>>>>>> >>>>>>>> (2013/03/05 22:10), Glauber Costa wrote: >>>>>>>>> >>>>>>>>> + case _MEMSWAP: { >>>>>>>>> + struct sysinfo i; >>>>>>>>> + si_swapinfo(&i); >>>>>>>>> + >>>>>>>>> + return ((memcg_read_root_rss() + >>>>>>>>> + atomic_long_read(&vm_stat[NR_FILE_PAGES])) << PAGE_SH= IFT) >>>>>>>>> + >>>>>>>>> + i.totalswap - i.freeswap; >>>>>>>> >>>>>>>> >>>>>>>> How swapcache is handled ? ...and How kmem works with this calc = ? >>>>>>>> >>>>>>> I am ignoring kmem, because we don't account kmem for the root cg= roup >>>>>>> anyway. >>>>>>> >>>>>>> Setting the limit is invalid, and we don't account until the limi= t is >>>>>>> set. Then it will be 0, always. >>>>>>> >>>>>>> For swapcache, I am hoping that totalswap - freeswap will cover >>>>>>> everything swap related. If you think I am wrong, please enlighte= n me. >>>>>>> >>>>>> >>>>>> i.totalswap - i.freeswap =3D # of used swap entries. >>>>>> >>>>>> SwapCache can be rss and used swap entry at the same time. >>>>>> >>>>> >>>>> Well, yes, but the rss entries would be accounted for in get_mm_rss= (), >>>>> won't they ? >>>>> >>>>> What am I missing ? >>>> >>>> >>>> >>>> I think the correct caluculation is >>>> >>>> Sum of all RSS + All file caches + (i.total_swap - i.freeswap - = # of >>>> mapped SwapCache) >>>> >>>> >>>> In the patch, mapped SwapCache is counted as both of rss and swap. >>>> >>> >>> After a quick look, swapcache is counted as file pages and meanwhile >>> use a swap entry at the same time(__add_to{delete_from}_swap_cache())= . >>> Even though, I think we still do not need to exclude swapcache out, >>> because it indeed uses two copy of resource: one is swap entry, one i= s >>> cache, so the usage should count both of them in. >>> >>> What I think it matters is that swapcache may be counted as both file >>> pages and rss(if it's a process's anonymous page), which we need to >>> subtract # of swapcache to avoid double-counting. But it isn't always >>> so: a shmem/tmpfs page may use swapcache and be counted as file pages >>> but not a rss, then we can not subtract swapcache... Is there anythin= g >>> I lost? >>> >> >> >> Please don't think difficult. All pages for user/caches are counted in >> LRU. All swap-entry usage can be cauht by total_swap_pages - nr_swap_p= ages. >> We just need to subtract number of swap-cache which is double counted >> as swap-entry and a page in LRU. >> >> NR_ACTIVE_ANON + NR_INACTIVE_ANON + NR_ACTIVE_FILE + NR_INACTIVE_FILE >> + NR_UNEVICTABLE + total_swap_pages - nr_swap_pages - NR_SWAP_CACHE >> > > Using LRU numbers is more suitable. But forgive me, I still doubt > whether we should subtract NR_SWAP_CACHE out because it uses both a > swap entry and a page cache and it isn't a real double counting. > Used swap entry can be reclaimed if there are SwapCache on memory. Thanks, =E3=83=BCKame -- 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/ . Don't email: email@kvack.org