From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail137.messagelabs.com (mail137.messagelabs.com [216.82.249.19]) by kanga.kvack.org (Postfix) with ESMTP id CA22C6B0011 for ; Thu, 19 May 2011 20:11:57 -0400 (EDT) Received: from hpaq3.eem.corp.google.com (hpaq3.eem.corp.google.com [172.25.149.3]) by smtp-out.google.com with ESMTP id p4K0BqfB023108 for ; Thu, 19 May 2011 17:11:53 -0700 Received: from qyk36 (qyk36.prod.google.com [10.241.83.164]) by hpaq3.eem.corp.google.com with ESMTP id p4K0Bohw026850 (version=TLSv1/SSLv3 cipher=RC4-SHA bits=128 verify=NOT) for ; Thu, 19 May 2011 17:11:51 -0700 Received: by qyk36 with SMTP id 36so186qyk.4 for ; Thu, 19 May 2011 17:11:50 -0700 (PDT) MIME-Version: 1.0 In-Reply-To: <20110520085152.e518ac71.kamezawa.hiroyu@jp.fujitsu.com> References: <1305826360-2167-1-git-send-email-yinghan@google.com> <1305826360-2167-3-git-send-email-yinghan@google.com> <20110520085152.e518ac71.kamezawa.hiroyu@jp.fujitsu.com> Date: Thu, 19 May 2011 17:11:49 -0700 Message-ID: Subject: Re: [PATCH V3 3/3] memcg: add memory.numastat api for numa statistics From: Ying Han Content-Type: multipart/alternative; boundary=002354470aa8d8c18804a3a9f7f8 Sender: owner-linux-mm@kvack.org List-ID: To: KAMEZAWA Hiroyuki Cc: KOSAKI Motohiro , Minchan Kim , Daisuke Nishimura , Balbir Singh , Tejun Heo , Pavel Emelyanov , Andrew Morton , Li Zefan , Mel Gorman , Christoph Lameter , Johannes Weiner , Rik van Riel , Hugh Dickins , Michal Hocko , Dave Hansen , Zhu Yanhai , linux-mm@kvack.org --002354470aa8d8c18804a3a9f7f8 Content-Type: text/plain; charset=ISO-8859-1 On Thu, May 19, 2011 at 4:51 PM, KAMEZAWA Hiroyuki < kamezawa.hiroyu@jp.fujitsu.com> wrote: > On Thu, 19 May 2011 10:32:40 -0700 > Ying Han wrote: > > > The new API exports numa_maps per-memcg basis. This is a piece of useful > > information where it exports per-memcg page distribution across real numa > > nodes. > > > > One of the usecase is evaluating application performance by combining > this > > information w/ the cpu allocation to the application. > > > > The output of the memory.numastat tries to follow w/ simiar format of > numa_maps > > like: > > > > total= N0= N1= ... > > file= N0= N1= ... > > anon= N0= N1= ... > > > > $ cat /dev/cgroup/memory/memory.numa_stat > > total=246594 N0=18225 N1=72025 N2=26378 N3=129966 > > file=221728 N0=15030 N1=60804 N2=23238 N3=122656 > > anon=21120 N0=2937 N1=7733 N2=3140 N3=7310 > > > > Hmm ? this doesn't seem consistent....Isn't this log updated ? > Nope. This is the V3 i posted w/ updated testing result. --Ying > > Thanks, > -Kame > > > change v3..v2: > > 1. calculate the "total" based on the per-memcg lru size instead of > rss+cache. > > this makes the "total" value to be consistant w/ the per-node values > follows > > after. > > > > change v2..v1: > > 1. add also the file and anon pages on per-node distribution. > > > > Signed-off-by: Ying Han > > --- > > mm/memcontrol.c | 120 > +++++++++++++++++++++++++++++++++++++++++++++++++++++++ > > 1 files changed, 120 insertions(+), 0 deletions(-) > > > > diff --git a/mm/memcontrol.c b/mm/memcontrol.c > > index e14677c..268d806 100644 > > --- a/mm/memcontrol.c > > +++ b/mm/memcontrol.c > > @@ -1162,6 +1162,73 @@ unsigned long mem_cgroup_zone_nr_lru_pages(struct > mem_cgroup *memcg, > > return MEM_CGROUP_ZSTAT(mz, lru); > > } > > > > + > > +unsigned long mem_cgroup_node_nr_file_lru_pages(struct mem_cgroup > *memcg, > > + int nid) > > +{ > > + unsigned long ret; > > + > > + ret = mem_cgroup_get_zonestat_node(memcg, nid, LRU_INACTIVE_FILE) + > > + mem_cgroup_get_zonestat_node(memcg, nid, LRU_ACTIVE_FILE); > > + > > + return ret; > > +} > > + > > +unsigned long mem_cgroup_nr_file_lru_pages(struct mem_cgroup *memcg) > > +{ > > + u64 total = 0; > > + int nid; > > + > > + for_each_node_state(nid, N_HIGH_MEMORY) > > + total += mem_cgroup_node_nr_file_lru_pages(memcg, nid); > > + > > + return total; > > +} > > + > > +unsigned long mem_cgroup_node_nr_anon_lru_pages(struct mem_cgroup > *memcg, > > + int nid) > > +{ > > + unsigned long ret; > > + > > + ret = mem_cgroup_get_zonestat_node(memcg, nid, LRU_INACTIVE_ANON) + > > + mem_cgroup_get_zonestat_node(memcg, nid, LRU_ACTIVE_ANON); > > + > > + return ret; > > +} > > + > > +unsigned long mem_cgroup_nr_anon_lru_pages(struct mem_cgroup *memcg) > > +{ > > + u64 total = 0; > > + int nid; > > + > > + for_each_node_state(nid, N_HIGH_MEMORY) > > + total += mem_cgroup_node_nr_anon_lru_pages(memcg, nid); > > + > > + return total; > > +} > > + > > +unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg, int > nid) > > +{ > > + enum lru_list l; > > + u64 total = 0; > > + > > + for_each_lru(l) > > + total += mem_cgroup_get_zonestat_node(memcg, nid, l); > > + > > + return total; > > +} > > + > > +unsigned long mem_cgroup_nr_lru_pages(struct mem_cgroup *memcg) > > +{ > > + u64 total = 0; > > + int nid; > > + > > + for_each_node_state(nid, N_HIGH_MEMORY) > > + total += mem_cgroup_node_nr_lru_pages(memcg, nid); > > + > > + return total; > > +} > > + > > struct zone_reclaim_stat *mem_cgroup_get_reclaim_stat(struct mem_cgroup > *memcg, > > struct zone *zone) > > { > > @@ -4048,6 +4115,41 @@ mem_cgroup_get_total_stat(struct mem_cgroup *mem, > struct mcs_total_stat *s) > > mem_cgroup_get_local_stat(iter, s); > > } > > > > +static int mem_control_numa_stat_show(struct seq_file *m, void *arg) > > +{ > > + int nid; > > + unsigned long total_nr, file_nr, anon_nr; > > + unsigned long node_nr; > > + struct cgroup *cont = m->private; > > + struct mem_cgroup *mem_cont = mem_cgroup_from_cont(cont); > > + > > + total_nr = mem_cgroup_nr_lru_pages(mem_cont); > > + seq_printf(m, "total=%lu", total_nr); > > + for_each_node_state(nid, N_HIGH_MEMORY) { > > + node_nr = mem_cgroup_node_nr_lru_pages(mem_cont, nid); > > + seq_printf(m, " N%d=%lu", nid, node_nr); > > + } > > + seq_putc(m, '\n'); > > + > > + file_nr = mem_cgroup_nr_file_lru_pages(mem_cont); > > + seq_printf(m, "file=%lu", file_nr); > > + for_each_node_state(nid, N_HIGH_MEMORY) { > > + node_nr = mem_cgroup_node_nr_file_lru_pages(mem_cont, nid); > > + seq_printf(m, " N%d=%lu", nid, node_nr); > > + } > > + seq_putc(m, '\n'); > > + > > + anon_nr = mem_cgroup_nr_anon_lru_pages(mem_cont); > > + seq_printf(m, "anon=%lu", anon_nr); > > + for_each_node_state(nid, N_HIGH_MEMORY) { > > + node_nr = mem_cgroup_node_nr_anon_lru_pages(mem_cont, nid); > > + seq_printf(m, " N%d=%lu", nid, node_nr); > > + } > > + seq_putc(m, '\n'); > > + > > + return 0; > > +} > > + > > static int mem_control_stat_show(struct cgroup *cont, struct cftype > *cft, > > struct cgroup_map_cb *cb) > > { > > @@ -4481,6 +4583,20 @@ static int mem_cgroup_oom_control_write(struct > cgroup *cgrp, > > return 0; > > } > > > > +static const struct file_operations > mem_control_numa_stat_file_operations = { > > + .read = seq_read, > > + .llseek = seq_lseek, > > + .release = single_release, > > +}; > > + > > +static int mem_control_numa_stat_open(struct inode *unused, struct file > *file) > > +{ > > + struct cgroup *cont = file->f_dentry->d_parent->d_fsdata; > > + > > + file->f_op = &mem_control_numa_stat_file_operations; > > + return single_open(file, mem_control_numa_stat_show, cont); > > +} > > + > > static struct cftype mem_cgroup_files[] = { > > { > > .name = "usage_in_bytes", > > @@ -4544,6 +4660,10 @@ static struct cftype mem_cgroup_files[] = { > > .unregister_event = mem_cgroup_oom_unregister_event, > > .private = MEMFILE_PRIVATE(_OOM_TYPE, OOM_CONTROL), > > }, > > + { > > + .name = "numa_stat", > > + .open = mem_control_numa_stat_open, > > + }, > > }; > > > > #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP > > -- > > 1.7.3.1 > > > > > > --002354470aa8d8c18804a3a9f7f8 Content-Type: text/html; charset=ISO-8859-1 Content-Transfer-Encoding: quoted-printable

On Thu, May 19, 2011 at 4:51 PM, KAMEZAW= A Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com> wrote:
On Thu, 19 May 2011 10:32:40 -0700
Ying Han <yinghan@google.com&g= t; wrote:

> The new API exports numa_maps per-memcg basis. This is a piece of usef= ul
> information where it exports per-memcg page distribution across real n= uma
> nodes.
>
> One of the usecase is evaluating application performance by combining = this
> information w/ the cpu allocation to the application.
>
> The output of the memory.numastat tries to follow w/ simiar format of = numa_maps
> like:
>
> total=3D<total pages> N0=3D<node 0 pages> N1=3D<node 1 = pages> ...
> file=3D<total file pages> N0=3D<node 0 pages> N1=3D<nod= e 1 pages> ...
> anon=3D<total anon pages> N0=3D<node 0 pages> N1=3D<nod= e 1 pages> ...
>
> $ cat /dev/cgroup/memory/memory.numa_stat
> total=3D246594 N0=3D18225 N1=3D72025 N2=3D26378 N3=3D129966
> file=3D221728 N0=3D15030 N1=3D60804 N2=3D23238 N3=3D122656
> anon=3D21120 N0=3D2937 N1=3D7733 N2=3D3140 N3=3D7310
>

Hmm ? this doesn't seem consistent....Isn't this log updated = ?

Nope. This is the V3 i posted w/ upda= ted testing result.

--Ying
=A0

Thanks,
-Kame

> change v3..v2:
> 1. calculate the "total" based on the per-memcg lru size ins= tead of rss+cache.
> this makes the "total" value to be consistant w/ the per-nod= e values follows
> after.
>
> change v2..v1:
> 1. add also the file and anon pages on per-node distribution.
>
> Signed-off-by: Ying Han <ying= han@google.com>
> ---
> =A0mm/memcontrol.c | =A0120 ++++++++++++++++++++++++++++++++++++++++++= +++++++++++++
> =A01 files changed, 120 insertions(+), 0 deletions(-)
>
> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> index e14677c..268d806 100644
> --- a/mm/memcontrol.c
> +++ b/mm/memcontrol.c
> @@ -1162,6 +1162,73 @@ unsigned long mem_cgroup_zone_nr_lru_pages(stru= ct mem_cgroup *memcg,
> =A0 =A0 =A0 return MEM_CGROUP_ZSTAT(mz, lru);
> =A0}
>
> +
> +unsigned long mem_cgroup_node_nr_file_lru_pages(struct mem_cgroup *me= mcg,
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 = =A0 =A0 =A0 =A0 =A0 int nid)
> +{
> + =A0 =A0 unsigned long ret;
> +
> + =A0 =A0 ret =3D mem_cgroup_get_zonestat_node(memcg, nid, LRU_INACTIV= E_FILE) +
> + =A0 =A0 =A0 =A0 =A0 =A0 mem_cgroup_get_zonestat_node(memcg, nid, LRU= _ACTIVE_FILE);
> +
> + =A0 =A0 return ret;
> +}
> +
> +unsigned long mem_cgroup_nr_file_lru_pages(struct mem_cgroup *memcg)<= br> > +{
> + =A0 =A0 u64 total =3D 0;
> + =A0 =A0 int nid;
> +
> + =A0 =A0 for_each_node_state(nid, N_HIGH_MEMORY)
> + =A0 =A0 =A0 =A0 =A0 =A0 total +=3D mem_cgroup_node_nr_file_lru_pages= (memcg, nid);
> +
> + =A0 =A0 return total;
> +}
> +
> +unsigned long mem_cgroup_node_nr_anon_lru_pages(struct mem_cgroup *me= mcg,
> + =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 = =A0 =A0 =A0 =A0 =A0 int nid)
> +{
> + =A0 =A0 unsigned long ret;
> +
> + =A0 =A0 ret =3D mem_cgroup_get_zonestat_node(memcg, nid, LRU_INACTIV= E_ANON) +
> + =A0 =A0 =A0 =A0 =A0 =A0 mem_cgroup_get_zonestat_node(memcg, nid, LRU= _ACTIVE_ANON);
> +
> + =A0 =A0 return ret;
> +}
> +
> +unsigned long mem_cgroup_nr_anon_lru_pages(struct mem_cgroup *memcg)<= br> > +{
> + =A0 =A0 u64 total =3D 0;
> + =A0 =A0 int nid;
> +
> + =A0 =A0 for_each_node_state(nid, N_HIGH_MEMORY)
> + =A0 =A0 =A0 =A0 =A0 =A0 total +=3D mem_cgroup_node_nr_anon_lru_pages= (memcg, nid);
> +
> + =A0 =A0 return total;
> +}
> +
> +unsigned long mem_cgroup_node_nr_lru_pages(struct mem_cgroup *memcg, = int nid)
> +{
> + =A0 =A0 enum lru_list l;
> + =A0 =A0 u64 total =3D 0;
> +
> + =A0 =A0 for_each_lru(l)
> + =A0 =A0 =A0 =A0 =A0 =A0 total +=3D mem_cgroup_get_zonestat_node(memc= g, nid, l);
> +
> + =A0 =A0 return total;
> +}
> +
> +unsigned long mem_cgroup_nr_lru_pages(struct mem_cgroup *memcg)
> +{
> + =A0 =A0 u64 total =3D 0;
> + =A0 =A0 int nid;
> +
> + =A0 =A0 for_each_node_state(nid, N_HIGH_MEMORY)
> + =A0 =A0 =A0 =A0 =A0 =A0 total +=3D mem_cgroup_node_nr_lru_pages(memc= g, nid);
> +
> + =A0 =A0 return total;
> +}
> +
> =A0struct zone_reclaim_stat *mem_cgroup_get_reclaim_stat(struct mem_cg= roup *memcg,
> =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 = =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 struct zone *zone)
> =A0{
> @@ -4048,6 +4115,41 @@ mem_cgroup_get_total_stat(struct mem_cgroup *me= m, struct mcs_total_stat *s)
> =A0 =A0 =A0 =A0 =A0 =A0 =A0 mem_cgroup_get_local_stat(iter, s);
> =A0}
>
> +static int mem_control_numa_stat_show(struct seq_file *m, void *arg)<= br> > +{
> + =A0 =A0 int nid;
> + =A0 =A0 unsigned long total_nr, file_nr, anon_nr;
> + =A0 =A0 unsigned long node_nr;
> + =A0 =A0 struct cgroup *cont =3D m->private;
> + =A0 =A0 struct mem_cgroup *mem_cont =3D mem_cgroup_from_cont(cont);<= br> > +
> + =A0 =A0 total_nr =3D mem_cgroup_nr_lru_pages(mem_cont);
> + =A0 =A0 seq_printf(m, "total=3D%lu", total_nr);
> + =A0 =A0 for_each_node_state(nid, N_HIGH_MEMORY) {
> + =A0 =A0 =A0 =A0 =A0 =A0 node_nr =3D mem_cgroup_node_nr_lru_pages(mem= _cont, nid);
> + =A0 =A0 =A0 =A0 =A0 =A0 seq_printf(m, " N%d=3D%lu", nid, n= ode_nr);
> + =A0 =A0 }
> + =A0 =A0 seq_putc(m, '\n');
> +
> + =A0 =A0 file_nr =3D mem_cgroup_nr_file_lru_pages(mem_cont);
> + =A0 =A0 seq_printf(m, "file=3D%lu", file_nr);
> + =A0 =A0 for_each_node_state(nid, N_HIGH_MEMORY) {
> + =A0 =A0 =A0 =A0 =A0 =A0 node_nr =3D mem_cgroup_node_nr_file_lru_page= s(mem_cont, nid);
> + =A0 =A0 =A0 =A0 =A0 =A0 seq_printf(m, " N%d=3D%lu", nid, n= ode_nr);
> + =A0 =A0 }
> + =A0 =A0 seq_putc(m, '\n');
> +
> + =A0 =A0 anon_nr =3D mem_cgroup_nr_anon_lru_pages(mem_cont);
> + =A0 =A0 seq_printf(m, "anon=3D%lu", anon_nr);
> + =A0 =A0 for_each_node_state(nid, N_HIGH_MEMORY) {
> + =A0 =A0 =A0 =A0 =A0 =A0 node_nr =3D mem_cgroup_node_nr_anon_lru_page= s(mem_cont, nid);
> + =A0 =A0 =A0 =A0 =A0 =A0 seq_printf(m, " N%d=3D%lu", nid, n= ode_nr);
> + =A0 =A0 }
> + =A0 =A0 seq_putc(m, '\n');
> +
> + =A0 =A0 return 0;
> +}
> +
> =A0static int mem_control_stat_show(struct cgroup *cont, struct cftype= *cft,
> =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0 =A0struct = cgroup_map_cb *cb)
> =A0{
> @@ -4481,6 +4583,20 @@ static int mem_cgroup_oom_control_write(struct = cgroup *cgrp,
> =A0 =A0 =A0 return 0;
> =A0}
>
> +static const struct file_operations mem_control_numa_stat_file_operat= ions =3D {
> + =A0 =A0 .read =3D seq_read,
> + =A0 =A0 .llseek =3D seq_lseek,
> + =A0 =A0 .release =3D single_release,
> +};
> +
> +static int mem_control_numa_stat_open(struct inode *unused, struct fi= le *file)
> +{
> + =A0 =A0 struct cgroup *cont =3D file->f_dentry->d_parent->d= _fsdata;
> +
> + =A0 =A0 file->f_op =3D &mem_control_numa_stat_file_operations= ;
> + =A0 =A0 return single_open(file, mem_control_numa_stat_show, cont);<= br> > +}
> +
> =A0static struct cftype mem_cgroup_files[] =3D {
> =A0 =A0 =A0 {
> =A0 =A0 =A0 =A0 =A0 =A0 =A0 .name =3D "usage_in_bytes",
> @@ -4544,6 +4660,10 @@ static struct cftype mem_cgroup_files[] =3D { > =A0 =A0 =A0 =A0 =A0 =A0 =A0 .unregister_event =3D mem_cgroup_oom_unreg= ister_event,
> =A0 =A0 =A0 =A0 =A0 =A0 =A0 .private =3D MEMFILE_PRIVATE(_OOM_TYPE, OO= M_CONTROL),
> =A0 =A0 =A0 },
> + =A0 =A0 {
> + =A0 =A0 =A0 =A0 =A0 =A0 .name =3D "numa_stat",
> + =A0 =A0 =A0 =A0 =A0 =A0 .open =3D mem_control_numa_stat_open,
> + =A0 =A0 },
> =A0};
>
> =A0#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
> --
> 1.7.3.1
>
>


--002354470aa8d8c18804a3a9f7f8-- -- 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: email@kvack.org