From: Pavel Emelyanov <xemul-GEFAQzZX7r8dnm+yROfE0A@public.gmane.org>
To: Balbir Singh
<balbir-23VcF4HTsmIX0ybBhKVfKdBPR1lH4CV8@public.gmane.org>,
KAMEZAWA Hiroyuki
<kamezawa.hiroyu-+CUm20s59erQFUHtdCDX3A@public.gmane.org>,
Paul Menage <menage-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>
Cc: Linux Containers
<containers-qjLDD68F18O7TbgM5vRIOg@public.gmane.org>,
Linux MM <linux-mm-Bw31MaZKKs3YtjvyW6yDsg@public.gmane.org>
Subject: [PATCH 2/2] Make res_counter hierarchical
Date: Fri, 07 Mar 2008 18:32:20 +0300 [thread overview]
Message-ID: <47D16004.7050204@openvz.org> (raw)
This allows us two things basically:
1. If the subgroup has the limit higher than its parent has
then the one will get more memory than allowed.
2. When we will need to account for a resource in more than
one place, we'll be able to use this technics.
Look, consider we have a memory limit and swap limit. The
memory limit is the limit for the sum of RSS, page cache
and swap usage. To account for this gracefuly, we'll set
two counters:
res_counter mem_counter;
res_counter swap_counter;
attach mm to the swap one
mm->mem_cnt = &swap_counter;
and make the swap_counter be mem's child. That's it. If we
want hierarchical support, then the tree will look like this:
mem_counter_top
swap_counter_top <- mm_struct living at top
mem_counter_sub
swap_counter_sub <- mm_struct living at sub
Signed-off-by: Pavel Emelyanov <xemul-GEFAQzZX7r8dnm+yROfE0A@public.gmane.org>
---
include/linux/res_counter.h | 11 ++++++++++-
kernel/res_counter.c | 36 +++++++++++++++++++++++++++++-------
mm/memcontrol.c | 9 ++++++---
3 files changed, 45 insertions(+), 11 deletions(-)
diff --git a/include/linux/res_counter.h b/include/linux/res_counter.h
index 2c4deb5..a27105e 100644
--- a/include/linux/res_counter.h
+++ b/include/linux/res_counter.h
@@ -41,6 +41,10 @@ struct res_counter {
* the routines below consider this to be IRQ-safe
*/
spinlock_t lock;
+ /*
+ * the parent counter. used for hierarchical resource accounting
+ */
+ struct res_counter *parent;
};
/**
@@ -80,7 +84,12 @@ enum {
* helpers for accounting
*/
-void res_counter_init(struct res_counter *counter);
+/*
+ * the parent pointer is set only once - during the counter
+ * initialization. caller then must itself provide that this
+ * pointer is valid during the new counter lifetime
+ */
+void res_counter_init(struct res_counter *counter, struct res_counter *parent);
/*
* charge - try to consume more resource.
diff --git a/kernel/res_counter.c b/kernel/res_counter.c
index f1f20c2..046f6f4 100644
--- a/kernel/res_counter.c
+++ b/kernel/res_counter.c
@@ -13,10 +13,11 @@
#include <linux/res_counter.h>
#include <linux/uaccess.h>
-void res_counter_init(struct res_counter *counter)
+void res_counter_init(struct res_counter *counter, struct res_counter *parent)
{
spin_lock_init(&counter->lock);
counter->limit = (unsigned long long)LLONG_MAX;
+ counter->parent = parent;
}
int res_counter_charge_locked(struct res_counter *counter, unsigned long val)
@@ -36,10 +37,26 @@ int res_counter_charge(struct res_counter *counter, unsigned long val)
{
int ret;
unsigned long flags;
+ struct res_counter *c, *unroll_c;
+
+ local_irq_save(flags);
+ for (c = counter; c != NULL; c = c->parent) {
+ spin_lock(&c->lock);
+ ret = res_counter_charge_locked(c, val);
+ spin_unlock(&c->lock);
+ if (ret < 0)
+ goto unroll;
+ }
+ local_irq_restore(flags);
+ return 0;
- spin_lock_irqsave(&counter->lock, flags);
- ret = res_counter_charge_locked(counter, val);
- spin_unlock_irqrestore(&counter->lock, flags);
+unroll:
+ for (unroll_c = counter; unroll_c != c; unroll_c = unroll_c->parent) {
+ spin_lock(&unroll_c->lock);
+ res_counter_uncharge_locked(unroll_c, val);
+ spin_unlock(&unroll_c->lock);
+ }
+ local_irq_restore(flags);
return ret;
}
@@ -54,10 +71,15 @@ void res_counter_uncharge_locked(struct res_counter *counter, unsigned long val)
void res_counter_uncharge(struct res_counter *counter, unsigned long val)
{
unsigned long flags;
+ struct res_counter *c;
- spin_lock_irqsave(&counter->lock, flags);
- res_counter_uncharge_locked(counter, val);
- spin_unlock_irqrestore(&counter->lock, flags);
+ local_irq_save(flags);
+ for (c = counter; c != NULL; c = c->parent) {
+ spin_lock(&c->lock);
+ res_counter_uncharge_locked(c, val);
+ spin_unlock(&c->lock);
+ }
+ local_irq_restore(flags);
}
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index e5c741a..61db79c 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -976,19 +976,22 @@ static void free_mem_cgroup_per_zone_info(struct mem_cgroup *mem, int node)
static struct cgroup_subsys_state *
mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
{
- struct mem_cgroup *mem;
+ struct mem_cgroup *mem, *parent;
int node;
if (unlikely((cont->parent) == NULL)) {
mem = &init_mem_cgroup;
init_mm.mem_cgroup = mem;
- } else
+ parent = NULL;
+ } else {
mem = kzalloc(sizeof(struct mem_cgroup), GFP_KERNEL);
+ parent = mem_cgroup_from_cont(cont->parent);
+ }
if (mem == NULL)
return ERR_PTR(-ENOMEM);
- res_counter_init(&mem->res);
+ res_counter_init(&mem->res, parent ? &parent->res : NULL);
memset(&mem->info, 0, sizeof(mem->info));
--
1.5.3.4
WARNING: multiple messages have this Message-ID (diff)
From: Pavel Emelyanov <xemul@openvz.org>
To: Balbir Singh <balbir@linux.vnet.ibm.com>,
KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>,
Paul Menage <menage@google.com>
Cc: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>,
Linux Containers <containers@lists.osdl.org>,
Linux MM <linux-mm@kvack.org>
Subject: [PATCH 2/2] Make res_counter hierarchical
Date: Fri, 07 Mar 2008 18:32:20 +0300 [thread overview]
Message-ID: <47D16004.7050204@openvz.org> (raw)
This allows us two things basically:
1. If the subgroup has the limit higher than its parent has
then the one will get more memory than allowed.
2. When we will need to account for a resource in more than
one place, we'll be able to use this technics.
Look, consider we have a memory limit and swap limit. The
memory limit is the limit for the sum of RSS, page cache
and swap usage. To account for this gracefuly, we'll set
two counters:
res_counter mem_counter;
res_counter swap_counter;
attach mm to the swap one
mm->mem_cnt = &swap_counter;
and make the swap_counter be mem's child. That's it. If we
want hierarchical support, then the tree will look like this:
mem_counter_top
swap_counter_top <- mm_struct living at top
mem_counter_sub
swap_counter_sub <- mm_struct living at sub
Signed-off-by: Pavel Emelyanov <xemul@openvz.org>
---
include/linux/res_counter.h | 11 ++++++++++-
kernel/res_counter.c | 36 +++++++++++++++++++++++++++++-------
mm/memcontrol.c | 9 ++++++---
3 files changed, 45 insertions(+), 11 deletions(-)
diff --git a/include/linux/res_counter.h b/include/linux/res_counter.h
index 2c4deb5..a27105e 100644
--- a/include/linux/res_counter.h
+++ b/include/linux/res_counter.h
@@ -41,6 +41,10 @@ struct res_counter {
* the routines below consider this to be IRQ-safe
*/
spinlock_t lock;
+ /*
+ * the parent counter. used for hierarchical resource accounting
+ */
+ struct res_counter *parent;
};
/**
@@ -80,7 +84,12 @@ enum {
* helpers for accounting
*/
-void res_counter_init(struct res_counter *counter);
+/*
+ * the parent pointer is set only once - during the counter
+ * initialization. caller then must itself provide that this
+ * pointer is valid during the new counter lifetime
+ */
+void res_counter_init(struct res_counter *counter, struct res_counter *parent);
/*
* charge - try to consume more resource.
diff --git a/kernel/res_counter.c b/kernel/res_counter.c
index f1f20c2..046f6f4 100644
--- a/kernel/res_counter.c
+++ b/kernel/res_counter.c
@@ -13,10 +13,11 @@
#include <linux/res_counter.h>
#include <linux/uaccess.h>
-void res_counter_init(struct res_counter *counter)
+void res_counter_init(struct res_counter *counter, struct res_counter *parent)
{
spin_lock_init(&counter->lock);
counter->limit = (unsigned long long)LLONG_MAX;
+ counter->parent = parent;
}
int res_counter_charge_locked(struct res_counter *counter, unsigned long val)
@@ -36,10 +37,26 @@ int res_counter_charge(struct res_counter *counter, unsigned long val)
{
int ret;
unsigned long flags;
+ struct res_counter *c, *unroll_c;
+
+ local_irq_save(flags);
+ for (c = counter; c != NULL; c = c->parent) {
+ spin_lock(&c->lock);
+ ret = res_counter_charge_locked(c, val);
+ spin_unlock(&c->lock);
+ if (ret < 0)
+ goto unroll;
+ }
+ local_irq_restore(flags);
+ return 0;
- spin_lock_irqsave(&counter->lock, flags);
- ret = res_counter_charge_locked(counter, val);
- spin_unlock_irqrestore(&counter->lock, flags);
+unroll:
+ for (unroll_c = counter; unroll_c != c; unroll_c = unroll_c->parent) {
+ spin_lock(&unroll_c->lock);
+ res_counter_uncharge_locked(unroll_c, val);
+ spin_unlock(&unroll_c->lock);
+ }
+ local_irq_restore(flags);
return ret;
}
@@ -54,10 +71,15 @@ void res_counter_uncharge_locked(struct res_counter *counter, unsigned long val)
void res_counter_uncharge(struct res_counter *counter, unsigned long val)
{
unsigned long flags;
+ struct res_counter *c;
- spin_lock_irqsave(&counter->lock, flags);
- res_counter_uncharge_locked(counter, val);
- spin_unlock_irqrestore(&counter->lock, flags);
+ local_irq_save(flags);
+ for (c = counter; c != NULL; c = c->parent) {
+ spin_lock(&c->lock);
+ res_counter_uncharge_locked(c, val);
+ spin_unlock(&c->lock);
+ }
+ local_irq_restore(flags);
}
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index e5c741a..61db79c 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -976,19 +976,22 @@ static void free_mem_cgroup_per_zone_info(struct mem_cgroup *mem, int node)
static struct cgroup_subsys_state *
mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
{
- struct mem_cgroup *mem;
+ struct mem_cgroup *mem, *parent;
int node;
if (unlikely((cont->parent) == NULL)) {
mem = &init_mem_cgroup;
init_mm.mem_cgroup = mem;
- } else
+ parent = NULL;
+ } else {
mem = kzalloc(sizeof(struct mem_cgroup), GFP_KERNEL);
+ parent = mem_cgroup_from_cont(cont->parent);
+ }
if (mem == NULL)
return ERR_PTR(-ENOMEM);
- res_counter_init(&mem->res);
+ res_counter_init(&mem->res, parent ? &parent->res : NULL);
memset(&mem->info, 0, sizeof(mem->info));
--
1.5.3.4
--
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: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next reply other threads:[~2008-03-07 15:32 UTC|newest]
Thread overview: 48+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-03-07 15:32 Pavel Emelyanov [this message]
2008-03-07 15:32 ` [PATCH 2/2] Make res_counter hierarchical Pavel Emelyanov
[not found] ` <47D16004.7050204-GEFAQzZX7r8dnm+yROfE0A@public.gmane.org>
2008-03-08 4:45 ` KAMEZAWA Hiroyuki
2008-03-08 4:45 ` KAMEZAWA Hiroyuki
[not found] ` <20080308134514.434f38f4.kamezawa.hiroyu-+CUm20s59erQFUHtdCDX3A@public.gmane.org>
2008-03-11 8:15 ` Pavel Emelyanov
2008-03-11 8:15 ` Pavel Emelyanov
[not found] ` <47D63FBC.1010805-GEFAQzZX7r8dnm+yROfE0A@public.gmane.org>
2008-03-11 8:32 ` KAMEZAWA Hiroyuki
2008-03-11 8:32 ` KAMEZAWA Hiroyuki
[not found] ` <20080311173225.937935eb.kamezawa.hiroyu-+CUm20s59erQFUHtdCDX3A@public.gmane.org>
2008-03-11 8:38 ` Pavel Emelyanov
2008-03-11 8:38 ` Pavel Emelyanov
[not found] ` <47D6451A.7090807-GEFAQzZX7r8dnm+yROfE0A@public.gmane.org>
2008-03-11 9:03 ` Daisuke Nishimura
2008-03-11 9:03 ` Daisuke Nishimura
2008-03-11 9:07 ` KAMEZAWA Hiroyuki
2008-03-11 9:07 ` KAMEZAWA Hiroyuki
2008-03-11 8:57 ` Paul Menage
2008-03-11 8:57 ` Paul Menage
[not found] ` <6599ad830803110157u71fe6c3cse125d0202610413b-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2008-03-11 9:13 ` KAMEZAWA Hiroyuki
2008-03-11 9:13 ` KAMEZAWA Hiroyuki
[not found] ` <20080311181325.c0bf6b90.kamezawa.hiroyu-+CUm20s59erQFUHtdCDX3A@public.gmane.org>
2008-03-11 9:11 ` Paul Menage
2008-03-11 9:11 ` Paul Menage
[not found] ` <6599ad830803110211u1cb48874l30aa75d21dc2b23-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2008-03-11 9:16 ` Balbir Singh
2008-03-11 9:16 ` Balbir Singh
[not found] ` <47D64E0A.3090907-23VcF4HTsmIX0ybBhKVfKdBPR1lH4CV8@public.gmane.org>
2008-03-11 9:39 ` KAMEZAWA Hiroyuki
2008-03-11 9:39 ` KAMEZAWA Hiroyuki
[not found] ` <20080311183940.11695e41.kamezawa.hiroyu-+CUm20s59erQFUHtdCDX3A@public.gmane.org>
2008-03-11 9:53 ` Balbir Singh
2008-03-11 9:53 ` Balbir Singh
[not found] ` <47D65680.4090106-23VcF4HTsmIX0ybBhKVfKdBPR1lH4CV8@public.gmane.org>
2008-03-11 10:03 ` KAMEZAWA Hiroyuki
2008-03-11 10:03 ` KAMEZAWA Hiroyuki
2008-03-11 15:56 ` Paul Menage
2008-03-11 15:56 ` Paul Menage
[not found] ` <6599ad830803110856j5333f032n2e26fb51111a839c-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2008-03-11 15:59 ` Balbir Singh
2008-03-11 15:59 ` Balbir Singh
2008-03-08 19:06 ` Balbir Singh
2008-03-08 19:06 ` Balbir Singh
[not found] ` <47D2E3C2.8050402-23VcF4HTsmIX0ybBhKVfKdBPR1lH4CV8@public.gmane.org>
2008-03-11 8:17 ` Pavel Emelyanov
2008-03-11 8:17 ` Pavel Emelyanov
[not found] ` <47D64037.3000705-GEFAQzZX7r8dnm+yROfE0A@public.gmane.org>
2008-03-11 8:24 ` Balbir Singh
2008-03-11 8:24 ` Balbir Singh
[not found] ` <47D641B8.5000701-23VcF4HTsmIX0ybBhKVfKdBPR1lH4CV8@public.gmane.org>
2008-03-11 8:40 ` Pavel Emelyanov
2008-03-11 8:40 ` Pavel Emelyanov
2008-03-12 23:05 ` YAMAMOTO Takashi
2008-03-12 23:05 ` YAMAMOTO Takashi
[not found] ` <20080312230541.CB9021E703D-Pcsii4f/SVk@public.gmane.org>
2008-03-12 23:36 ` YAMAMOTO Takashi
2008-03-12 23:36 ` YAMAMOTO Takashi
2008-03-13 8:56 ` Pavel Emelyanov
2008-03-13 8:56 ` Pavel Emelyanov
2008-04-02 15:26 ` Balbir Singh
[not found] ` <47F3A5BF.1080301-23VcF4HTsmIX0ybBhKVfKdBPR1lH4CV8@public.gmane.org>
2008-04-03 12:26 ` Pavel Emelyanov
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=47D16004.7050204@openvz.org \
--to=xemul-gefaqzzx7r8dnm+yrofe0a@public.gmane.org \
--cc=balbir-23VcF4HTsmIX0ybBhKVfKdBPR1lH4CV8@public.gmane.org \
--cc=containers-qjLDD68F18O7TbgM5vRIOg@public.gmane.org \
--cc=kamezawa.hiroyu-+CUm20s59erQFUHtdCDX3A@public.gmane.org \
--cc=linux-mm-Bw31MaZKKs3YtjvyW6yDsg@public.gmane.org \
--cc=menage-hpIqsD4AKlfQT0dZR+AlfA@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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.