From: Ying Han <yinghan@google.com>
To: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>,
Minchan Kim <minchan.kim@gmail.com>,
Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>,
Balbir Singh <balbir@linux.vnet.ibm.com>,
Tejun Heo <tj@kernel.org>, Pavel Emelyanov <xemul@openvz.org>,
KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>,
Andrew Morton <akpm@linux-foundation.org>,
Li Zefan <lizf@cn.fujitsu.com>, Mel Gorman <mel@csn.ul.ie>,
Christoph Lameter <cl@linux.com>,
Johannes Weiner <hannes@cmpxchg.org>,
Rik van Riel <riel@redhat.com>, Hugh Dickins <hughd@google.com>,
Michal Hocko <mhocko@suse.cz>,
Dave Hansen <dave@linux.vnet.ibm.com>,
Zhu Yanhai <zhu.yanhai@gmail.com>
Cc: linux-mm@kvack.org
Subject: [PATCH V7 3/9] New APIs to adjust per-memcg wmarks
Date: Thu, 21 Apr 2011 21:24:14 -0700 [thread overview]
Message-ID: <1303446260-21333-4-git-send-email-yinghan@google.com> (raw)
In-Reply-To: <1303446260-21333-1-git-send-email-yinghan@google.com>
Add memory.low_wmark_distance, memory.high_wmark_distance and reclaim_wmarks
APIs per-memcg. The first two adjust the internal low/high wmark calculation
and the reclaim_wmarks exports the current value of watermarks.
By default, the low/high_wmark is calculated by subtracting the distance from
the hard_limit(limit_in_bytes). When configuring the low/high_wmark distance,
user must setup the high_wmark_distance before low_wmark_distance. Also user
must zero low_wmark_distance before high_wmark_distance.
$ echo 500m >/dev/cgroup/A/memory.limit_in_bytes
$ cat /dev/cgroup/A/memory.limit_in_bytes
524288000
$ echo 50m >/dev/cgroup/A/memory.high_wmark_distance
$ echo 40m >/dev/cgroup/A/memory.low_wmark_distance
$ cat /dev/cgroup/A/memory.reclaim_wmarks
low_wmark 482344960
high_wmark 471859200
change v5..v4
1. add sanity check for setting high/low_wmark_distance for root cgroup.
changelog v4..v3:
1. replace the "wmark_ratio" API with individual tunable for low/high_wmarks.
changelog v3..v2:
1. replace the "min_free_kbytes" api with "wmark_ratio". This is part of
feedbacks
Signed-off-by: Ying Han <yinghan@google.com>
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
---
mm/memcontrol.c | 101 +++++++++++++++++++++++++++++++++++++++++++++++++++++++
1 files changed, 101 insertions(+), 0 deletions(-)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index c351e62..6029f1b 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3974,6 +3974,78 @@ static int mem_cgroup_swappiness_write(struct cgroup *cgrp, struct cftype *cft,
return 0;
}
+static u64 mem_cgroup_high_wmark_distance_read(struct cgroup *cgrp,
+ struct cftype *cft)
+{
+ struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
+
+ return memcg->high_wmark_distance;
+}
+
+static u64 mem_cgroup_low_wmark_distance_read(struct cgroup *cgrp,
+ struct cftype *cft)
+{
+ struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp);
+
+ return memcg->low_wmark_distance;
+}
+
+static int mem_cgroup_high_wmark_distance_write(struct cgroup *cont,
+ struct cftype *cft,
+ const char *buffer)
+{
+ struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
+ u64 low_wmark_distance = memcg->low_wmark_distance;
+ unsigned long long val;
+ u64 limit;
+ int ret;
+
+ if (!cont->parent)
+ return -EINVAL;
+
+ ret = res_counter_memparse_write_strategy(buffer, &val);
+ if (ret)
+ return -EINVAL;
+
+ limit = res_counter_read_u64(&memcg->res, RES_LIMIT);
+ if ((val >= limit) || (val < low_wmark_distance) ||
+ (low_wmark_distance && val == low_wmark_distance))
+ return -EINVAL;
+
+ memcg->high_wmark_distance = val;
+
+ setup_per_memcg_wmarks(memcg);
+ return 0;
+}
+
+static int mem_cgroup_low_wmark_distance_write(struct cgroup *cont,
+ struct cftype *cft,
+ const char *buffer)
+{
+ struct mem_cgroup *memcg = mem_cgroup_from_cont(cont);
+ u64 high_wmark_distance = memcg->high_wmark_distance;
+ unsigned long long val;
+ u64 limit;
+ int ret;
+
+ if (!cont->parent)
+ return -EINVAL;
+
+ ret = res_counter_memparse_write_strategy(buffer, &val);
+ if (ret)
+ return -EINVAL;
+
+ limit = res_counter_read_u64(&memcg->res, RES_LIMIT);
+ if ((val >= limit) || (val > high_wmark_distance) ||
+ (high_wmark_distance && val == high_wmark_distance))
+ return -EINVAL;
+
+ memcg->low_wmark_distance = val;
+
+ setup_per_memcg_wmarks(memcg);
+ return 0;
+}
+
static void __mem_cgroup_threshold(struct mem_cgroup *memcg, bool swap)
{
struct mem_cgroup_threshold_ary *t;
@@ -4265,6 +4337,21 @@ static void mem_cgroup_oom_unregister_event(struct cgroup *cgrp,
mutex_unlock(&memcg_oom_mutex);
}
+static int mem_cgroup_wmark_read(struct cgroup *cgrp,
+ struct cftype *cft, struct cgroup_map_cb *cb)
+{
+ struct mem_cgroup *mem = mem_cgroup_from_cont(cgrp);
+ u64 low_wmark, high_wmark;
+
+ low_wmark = res_counter_read_u64(&mem->res, RES_LOW_WMARK_LIMIT);
+ high_wmark = res_counter_read_u64(&mem->res, RES_HIGH_WMARK_LIMIT);
+
+ cb->fill(cb, "low_wmark", low_wmark);
+ cb->fill(cb, "high_wmark", high_wmark);
+
+ return 0;
+}
+
static int mem_cgroup_oom_control_read(struct cgroup *cgrp,
struct cftype *cft, struct cgroup_map_cb *cb)
{
@@ -4368,6 +4455,20 @@ static struct cftype mem_cgroup_files[] = {
.unregister_event = mem_cgroup_oom_unregister_event,
.private = MEMFILE_PRIVATE(_OOM_TYPE, OOM_CONTROL),
},
+ {
+ .name = "high_wmark_distance",
+ .write_string = mem_cgroup_high_wmark_distance_write,
+ .read_u64 = mem_cgroup_high_wmark_distance_read,
+ },
+ {
+ .name = "low_wmark_distance",
+ .write_string = mem_cgroup_low_wmark_distance_write,
+ .read_u64 = mem_cgroup_low_wmark_distance_read,
+ },
+ {
+ .name = "reclaim_wmarks",
+ .read_map = mem_cgroup_wmark_read,
+ },
};
#ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
--
1.7.3.1
--
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>
next prev parent reply other threads:[~2011-04-22 4:26 UTC|newest]
Thread overview: 48+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-04-22 4:24 [RFC PATCH V7 0/9] memcg: per cgroup background reclaim Ying Han
2011-04-22 4:24 ` [PATCH V7 1/9] Add kswapd descriptor Ying Han
2011-04-22 4:31 ` KAMEZAWA Hiroyuki
2011-04-22 4:47 ` KOSAKI Motohiro
2011-04-22 5:55 ` Ying Han
2011-04-22 4:24 ` [PATCH V7 2/9] Add per memcg reclaim watermarks Ying Han
2011-04-22 4:24 ` Ying Han [this message]
2011-04-22 4:32 ` [PATCH V7 3/9] New APIs to adjust per-memcg wmarks KAMEZAWA Hiroyuki
2011-04-22 4:24 ` [PATCH V7 4/9] Add memcg kswapd thread pool Ying Han
2011-04-22 4:36 ` KAMEZAWA Hiroyuki
2011-04-22 4:49 ` Ying Han
2011-04-22 5:00 ` KAMEZAWA Hiroyuki
2011-04-22 5:53 ` Ying Han
2011-04-22 5:59 ` KAMEZAWA Hiroyuki
2011-04-22 6:10 ` Ying Han
2011-04-22 7:46 ` KAMEZAWA Hiroyuki
2011-04-22 7:59 ` Ying Han
2011-04-22 8:02 ` KAMEZAWA Hiroyuki
2011-04-24 23:26 ` KAMEZAWA Hiroyuki
2011-04-25 2:08 ` Ying Han
2011-04-22 6:02 ` Zhu Yanhai
2011-04-22 6:14 ` Ying Han
2011-04-22 5:39 ` KOSAKI Motohiro
2011-04-22 5:56 ` KAMEZAWA Hiroyuki
2011-04-22 4:24 ` [PATCH V7 5/9] Infrastructure to support per-memcg reclaim Ying Han
2011-04-22 4:38 ` KAMEZAWA Hiroyuki
2011-04-22 5:11 ` KOSAKI Motohiro
2011-04-22 5:59 ` Ying Han
2011-04-22 5:27 ` KOSAKI Motohiro
2011-04-22 6:00 ` Ying Han
2011-04-22 4:24 ` [PATCH V7 6/9] Implement the select_victim_node within memcg Ying Han
2011-04-22 4:39 ` KAMEZAWA Hiroyuki
2011-04-22 4:24 ` [PATCH V7 7/9] Per-memcg background reclaim Ying Han
2011-04-22 4:40 ` KAMEZAWA Hiroyuki
2011-04-22 6:00 ` KOSAKI Motohiro
2011-04-22 7:54 ` Ying Han
2011-04-22 8:44 ` KOSAKI Motohiro
2011-04-22 18:37 ` Ying Han
2011-04-25 2:21 ` [PATCH] vmscan,memcg: memcg aware swap token KOSAKI Motohiro
2011-04-25 9:47 ` KAMEZAWA Hiroyuki
2011-04-25 17:13 ` Ying Han
2011-04-26 2:08 ` KOSAKI Motohiro
2011-04-22 4:24 ` [PATCH V7 8/9] Add per-memcg zone "unreclaimable" Ying Han
2011-04-22 4:43 ` KAMEZAWA Hiroyuki
2011-04-22 6:13 ` KOSAKI Motohiro
2011-04-22 6:17 ` Ying Han
2011-04-22 4:24 ` [PATCH V7 9/9] Enable per-memcg background reclaim Ying Han
2011-04-22 4:44 ` 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=1303446260-21333-4-git-send-email-yinghan@google.com \
--to=yinghan@google.com \
--cc=akpm@linux-foundation.org \
--cc=balbir@linux.vnet.ibm.com \
--cc=cl@linux.com \
--cc=dave@linux.vnet.ibm.com \
--cc=hannes@cmpxchg.org \
--cc=hughd@google.com \
--cc=kamezawa.hiroyu@jp.fujitsu.com \
--cc=kosaki.motohiro@jp.fujitsu.com \
--cc=linux-mm@kvack.org \
--cc=lizf@cn.fujitsu.com \
--cc=mel@csn.ul.ie \
--cc=mhocko@suse.cz \
--cc=minchan.kim@gmail.com \
--cc=nishimura@mxp.nes.nec.co.jp \
--cc=riel@redhat.com \
--cc=tj@kernel.org \
--cc=xemul@openvz.org \
--cc=zhu.yanhai@gmail.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).