From: Pavel Emelianov <xemul@sw.ru>
To: Andrew Morton <akpm@osdl.org>, Paul Menage <menage@google.com>,
Srivatsa Vaddagiri <vatsa@in.ibm.com>,
Balbir Singh <balbir@in.ibm.com>
Cc: devel@openvz.org,
Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
containers@lists.osdl.org, Kirill Korotaev <dev@sw.ru>
Subject: [RFC][PATCH 2/7] RSS controller core
Date: Tue, 06 Mar 2007 17:55:29 +0300 [thread overview]
Message-ID: <45ED80E1.7030406@sw.ru> (raw)
In-Reply-To: <45ED7DEC.7010403@sw.ru>
[-- Attachment #1: Type: text/plain, Size: 159 bytes --]
This includes setup of RSS container within generic
process containers, all the declarations used in RSS
accounting, and core code responsible for accounting.
[-- Attachment #2: diff-rss-container-core --]
[-- Type: text/plain, Size: 9872 bytes --]
diff -upr linux-2.6.20.orig/include/linux/rss_container.h linux-2.6.20-0/include/linux/rss_container.h
--- linux-2.6.20.orig/include/linux/rss_container.h 2007-03-06 13:39:17.000000000 +0300
+++ linux-2.6.20-0/include/linux/rss_container.h 2007-03-06 13:33:28.000000000 +0300
@@ -0,0 +1,68 @@
+#ifndef __RSS_CONTAINER_H__
+#define __RSS_CONTAINER_H__
+/*
+ * RSS container
+ *
+ * Copyright 2007 OpenVZ SWsoft Inc
+ *
+ * Author: Pavel Emelianov <xemul@openvz.org>
+ *
+ */
+
+struct page_container;
+struct rss_container;
+
+#ifdef CONFIG_RSS_CONTAINER
+int container_rss_prepare(struct page *, struct vm_area_struct *vma,
+ struct page_container **);
+
+void container_rss_add(struct page_container *);
+void container_rss_del(struct page_container *);
+void container_rss_release(struct page_container *);
+
+int mm_init_container(struct mm_struct *mm, struct task_struct *tsk);
+void mm_free_container(struct mm_struct *mm);
+
+unsigned long container_isolate_pages(unsigned long nr_to_scan,
+ struct rss_container *rss, struct list_head *dst,
+ int active, unsigned long *scanned);
+unsigned long container_nr_physpages(struct rss_container *rss);
+
+unsigned long container_try_to_free_pages(struct rss_container *);
+void container_out_of_memory(struct rss_container *);
+
+void container_rss_init_early(void);
+#else
+static inline int container_rss_prepare(struct page *pg,
+ struct vm_area_struct *vma, struct page_container **pc)
+{
+ *pc = NULL; /* to make gcc happy */
+ return 0;
+}
+
+static inline void container_rss_add(struct page_container *pc)
+{
+}
+
+static inline void container_rss_del(struct page_container *pc)
+{
+}
+
+static inline void container_rss_release(struct page_container *pc)
+{
+}
+
+static inline int mm_init_container(struct mm_struct *mm, struct task_struct *t)
+{
+ return 0;
+}
+
+static inline void mm_free_container(struct mm_struct *mm)
+{
+}
+
+static inline void container_rss_init_early(void)
+{
+}
+#endif
+#endif
diff -upr linux-2.6.20.orig/init/Kconfig linux-2.6.20-0/init/Kconfig
--- linux-2.6.20.orig/init/Kconfig 2007-03-06 13:33:28.000000000 +0300
+++ linux-2.6.20-0/init/Kconfig 2007-03-06 13:33:28.000000000 +0300
@@ -265,6 +265,13 @@ config CPUSETS
bool
select CONTAINERS
+config RSS_CONTAINER
+ bool "RSS accounting container"
+ select RESOURCE_COUNTERS
+ help
+ Provides a simple Resource Controller for monitoring and
+ controlling the total Resident Set Size of the tasks in a container
+
config SYSFS_DEPRECATED
bool "Create deprecated sysfs files"
default y
diff -upr linux-2.6.20.orig/mm/Makefile linux-2.6.20-0/mm/Makefile
--- linux-2.6.20.orig/mm/Makefile 2007-02-04 21:44:54.000000000 +0300
+++ linux-2.6.20-0/mm/Makefile 2007-03-06 13:33:28.000000000 +0300
@@ -29,3 +29,5 @@ obj-$(CONFIG_MEMORY_HOTPLUG) += memory_h
obj-$(CONFIG_FS_XIP) += filemap_xip.o
obj-$(CONFIG_MIGRATION) += migrate.o
obj-$(CONFIG_SMP) += allocpercpu.o
+
+obj-$(CONFIG_RSS_CONTAINER) += rss_container.o
diff -upr linux-2.6.20.orig/mm/rss_container.c linux-2.6.20-0/mm/rss_container.c
--- linux-2.6.20.orig/mm/rss_container.c 2007-03-06 13:39:17.000000000 +0300
+++ linux-2.6.20-0/mm/rss_container.c 2007-03-06 13:33:28.000000000 +0300
@@ -0,0 +1,307 @@
+/*
+ * RSS accounting container
+ *
+ * Copyright 2007 OpenVZ SWsoft Inc
+ *
+ * Author: Pavel Emelianov <xemul@openvz.org>
+ *
+ */
+
+#include <linux/list.h>
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/res_counter.h>
+#include <linux/rss_container.h>
+
+static struct container_subsys rss_subsys;
+
+struct rss_container {
+ struct res_counter res;
+ struct list_head page_list;
+ struct container_subsys_state css;
+};
+
+struct page_container {
+ struct page *page;
+ struct rss_container *cnt;
+ struct list_head list;
+};
+
+static inline struct rss_container *rss_from_cont(struct container *cnt)
+{
+ return container_of(container_subsys_state(cnt, &rss_subsys),
+ struct rss_container, css);
+}
+
+int mm_init_container(struct mm_struct *mm, struct task_struct *tsk)
+{
+ struct rss_container *cnt;
+
+ cnt = rss_from_cont(task_container(tsk, &rss_subsys));
+ if (css_get(&cnt->css))
+ return -EBUSY;
+
+ mm->rss_container = cnt;
+ return 0;
+}
+
+void mm_free_container(struct mm_struct *mm)
+{
+ css_put(&mm->rss_container->css);
+}
+
+int container_rss_prepare(struct page *page, struct vm_area_struct *vma,
+ struct page_container **ppc)
+{
+ struct rss_container *rss;
+ struct page_container *pc;
+
+ rcu_read_lock();
+ rss = rcu_dereference(vma->vm_mm->rss_container);
+ css_get_current(&rss->css);
+ rcu_read_unlock();
+
+ pc = kmalloc(sizeof(struct page_container), GFP_KERNEL);
+ if (pc == NULL)
+ goto out_nomem;
+
+ while (res_counter_charge(&rss->res, 1)) {
+ if (container_try_to_free_pages(rss))
+ continue;
+
+ container_out_of_memory(rss);
+ if (test_thread_flag(TIF_MEMDIE))
+ goto out_charge;
+ }
+
+ pc->page = page;
+ pc->cnt = rss;
+ *ppc = pc;
+ return 0;
+
+out_charge:
+ kfree(pc);
+out_nomem:
+ css_put(&rss->css);
+ return -ENOMEM;
+}
+
+void container_rss_release(struct page_container *pc)
+{
+ struct rss_container *rss;
+
+ rss = pc->cnt;
+ res_counter_uncharge(&rss->res, 1);
+ css_put(&rss->css);
+ kfree(pc);
+}
+
+void container_rss_add(struct page_container *pc)
+{
+ struct page *pg;
+ struct rss_container *rss;
+
+ pg = pc->page;
+ rss = pc->cnt;
+
+ spin_lock(&rss->res.lock);
+ list_add(&pc->list, &rss->page_list);
+ spin_unlock(&rss->res.lock);
+
+ page_container(pg) = pc;
+}
+
+void container_rss_del(struct page_container *pc)
+{
+ struct page *page;
+ struct rss_container *rss;
+
+ page = pc->page;
+ rss = pc->cnt;
+
+ spin_lock(&rss->res.lock);
+ list_del(&pc->list);
+ res_counter_uncharge_locked(&rss->res, 1);
+ spin_unlock(&rss->res.lock);
+
+ css_put(&rss->css);
+ kfree(pc);
+}
+
+unsigned long container_isolate_pages(unsigned long nr_to_scan,
+ struct rss_container *rss, struct list_head *dst,
+ int active, unsigned long *scanned)
+{
+ unsigned long nr_taken = 0;
+ struct page *page;
+ struct page_container *pc;
+ unsigned long scan;
+ struct list_head *src;
+ LIST_HEAD(pc_list);
+ struct zone *z;
+
+ spin_lock_irq(&rss->res.lock);
+ src = &rss->page_list;
+
+ for (scan = 0; scan < nr_to_scan && !list_empty(src); scan++) {
+ pc = list_entry(src->prev, struct page_container, list);
+ page = pc->page;
+ z = page_zone(page);
+
+ list_move(&pc->list, &pc_list);
+
+ spin_lock(&z->lru_lock);
+ if (PageLRU(page)) {
+ if ((active && PageActive(page)) ||
+ (!active && !PageActive(page))) {
+ if (likely(get_page_unless_zero(page))) {
+ ClearPageLRU(page);
+ nr_taken++;
+ list_move(&page->lru, dst);
+ }
+ }
+ }
+ spin_unlock(&z->lru_lock);
+ }
+
+ list_splice(&pc_list, src);
+ spin_unlock_irq(&rss->res.lock);
+
+ *scanned = scan;
+ return nr_taken;
+}
+
+unsigned long container_nr_physpages(struct rss_container *rss)
+{
+ return rss->res.usage;
+}
+
+static void rss_move_task(struct container_subsys *ss,
+ struct container *cont,
+ struct container *old_cont,
+ struct task_struct *p)
+{
+ struct mm_struct *mm;
+ struct rss_container *rss, *old_rss;
+
+ mm = get_task_mm(p);
+ if (mm == NULL)
+ goto out;
+
+ rss = rss_from_cont(cont);
+ old_rss = rss_from_cont(old_cont);
+ if (old_rss != mm->rss_container)
+ goto out_put;
+
+ css_get_current(&rss->css);
+ rcu_assign_pointer(mm->rss_container, rss);
+ css_put(&old_rss->css);
+
+out_put:
+ mmput(mm);
+out:
+ return;
+}
+
+static int rss_create(struct container_subsys *ss, struct container *cont)
+{
+ struct rss_container *rss;
+
+ rss = kzalloc(sizeof(struct rss_container), GFP_KERNEL);
+ if (rss == NULL)
+ return -ENOMEM;
+
+ res_counter_init(&rss->res);
+ INIT_LIST_HEAD(&rss->page_list);
+ cont->subsys[rss_subsys.subsys_id] = &rss->css;
+ return 0;
+}
+
+static void rss_destroy(struct container_subsys *ss,
+ struct container *cont)
+{
+ kfree(rss_from_cont(cont));
+}
+
+
+static ssize_t rss_read(struct container *cont, struct cftype *cft,
+ struct file *file, char __user *userbuf,
+ size_t nbytes, loff_t *ppos)
+{
+ return res_counter_read(&rss_from_cont(cont)->res, cft->private,
+ userbuf, nbytes, ppos);
+}
+
+static ssize_t rss_write(struct container *cont, struct cftype *cft,
+ struct file *file, const char __user *userbuf,
+ size_t nbytes, loff_t *ppos)
+{
+ return res_counter_write(&rss_from_cont(cont)->res, cft->private,
+ userbuf, nbytes, ppos);
+}
+
+
+static struct cftype rss_usage = {
+ .name = "rss_usage",
+ .private = RES_USAGE,
+ .read = rss_read,
+};
+
+static struct cftype rss_limit = {
+ .name = "rss_limit",
+ .private = RES_LIMIT,
+ .read = rss_read,
+ .write = rss_write,
+};
+
+static struct cftype rss_failcnt = {
+ .name = "rss_failcnt",
+ .private = RES_FAILCNT,
+ .read = rss_read,
+};
+
+static int rss_populate(struct container_subsys *ss,
+ struct container *cont)
+{
+ int rc;
+
+ if ((rc = container_add_file(cont, &rss_usage)) < 0)
+ return rc;
+ if ((rc = container_add_file(cont, &rss_failcnt)) < 0)
+ return rc;
+ if ((rc = container_add_file(cont, &rss_limit)) < 0)
+ return rc;
+
+ return 0;
+}
+
+static struct rss_container init_rss_container;
+
+static __init int rss_create_early(struct container_subsys *ss,
+ struct container *cont)
+{
+ struct rss_container *rss;
+
+ rss = &init_rss_container;
+ res_counter_init(&rss->res);
+ INIT_LIST_HEAD(&rss->page_list);
+ cont->subsys[rss_subsys.subsys_id] = &rss->css;
+ ss->create = rss_create;
+ return 0;
+}
+
+static struct container_subsys rss_subsys = {
+ .name = "rss",
+ .create = rss_create_early,
+ .destroy = rss_destroy,
+ .populate = rss_populate,
+ .attach = rss_move_task,
+};
+
+void __init container_rss_init_early(void)
+{
+ container_register_subsys(&rss_subsys);
+ init_mm.rss_container = rss_from_cont(
+ task_container(&init_task, &rss_subsys));
+ css_get_current(&init_mm.rss_container->css);
+}
next prev parent reply other threads:[~2007-03-06 14:52 UTC|newest]
Thread overview: 129+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-03-06 14:42 [RFC][PATCH 0/7] Resource controllers based on process containers Pavel Emelianov
2007-03-06 14:49 ` [RFC][PATCH 1/7] Resource counters Pavel Emelianov
2007-03-07 4:03 ` Balbir Singh
2007-03-07 7:19 ` Pavel Emelianov
2007-03-09 16:37 ` Herbert Poetzl
2007-03-11 9:01 ` Pavel Emelianov
2007-03-11 19:00 ` Eric W. Biederman
2007-03-12 1:16 ` Herbert Poetzl
2007-03-13 9:09 ` Eric W. Biederman
2007-03-13 9:27 ` Pavel Emelianov
2007-03-13 9:49 ` [Devel] " Kirill Korotaev
2007-03-13 15:21 ` Herbert Poetzl
2007-03-13 15:41 ` Pavel Emelianov
2007-03-13 16:07 ` Srivatsa Vaddagiri
2007-03-14 7:12 ` Pavel Emelianov
2007-03-15 16:51 ` Eric W. Biederman
2007-03-13 16:32 ` Herbert Poetzl
2007-03-06 14:55 ` Pavel Emelianov [this message]
2007-03-06 22:00 ` [RFC][PATCH 2/7] RSS controller core Andrew Morton
2007-03-09 16:48 ` Herbert Poetzl
2007-03-11 9:08 ` Pavel Emelianov
2007-03-11 14:32 ` Herbert Poetzl
2007-03-11 15:04 ` Pavel Emelianov
2007-03-12 0:41 ` Herbert Poetzl
2007-03-12 8:31 ` Pavel Emelianov
2007-03-12 9:55 ` Balbir Singh
2007-03-12 23:43 ` Herbert Poetzl
2007-03-13 1:57 ` Balbir Singh
2007-03-13 2:24 ` Srivatsa Vaddagiri
2007-03-13 16:06 ` Herbert Poetzl
2007-03-11 12:26 ` Kirill Korotaev
2007-03-11 12:51 ` Andrew Morton
2007-03-11 15:51 ` Balbir Singh
2007-03-11 19:34 ` Eric W. Biederman
2007-03-12 9:23 ` [Devel] " Kirill Korotaev
2007-03-13 9:26 ` Eric W. Biederman
2007-03-13 15:43 ` Kirill Korotaev
2007-03-12 1:00 ` Herbert Poetzl
2007-03-12 9:02 ` Pavel Emelianov
2007-03-12 21:11 ` Herbert Poetzl
2007-03-13 7:17 ` Pavel Emelianov
2007-03-13 15:05 ` Herbert Poetzl
2007-03-13 15:32 ` Pavel Emelianov
2007-03-13 15:10 ` Kirill Korotaev
2007-03-13 15:11 ` Herbert Poetzl
2007-03-13 15:54 ` Kirill Korotaev
2007-03-12 18:42 ` Dave Hansen
2007-03-12 22:41 ` Herbert Poetzl
2007-03-12 23:02 ` Dave Hansen
2007-03-18 16:58 ` Eric W. Biederman
2007-03-13 6:04 ` Andrew Morton
2007-03-13 10:19 ` [Devel] " Kirill Korotaev
2007-03-13 11:48 ` Andrew Morton
2007-03-13 14:59 ` Herbert Poetzl
2007-03-13 17:05 ` Dave Hansen
2007-03-14 15:38 ` Mel Gorman
2007-03-14 20:42 ` Dave Hansen
2007-03-20 18:57 ` Mel Gorman
2007-03-18 22:44 ` [Devel] " Paul Menage
2007-03-19 17:41 ` Eric W. Biederman
2007-03-13 17:26 ` Dave Hansen
2007-03-13 19:09 ` Alan Cox
2007-03-13 20:28 ` Dave Hansen
2007-03-16 0:55 ` Eric W. Biederman
2007-03-16 16:31 ` Dave Hansen
2007-03-16 18:54 ` Eric W. Biederman
2007-03-16 19:46 ` Dave Hansen
2007-03-18 17:42 ` Eric W. Biederman
2007-03-19 15:48 ` Herbert Poetzl
2007-03-20 16:15 ` controlling mmap()'d vs read/write() pages Dave Hansen
2007-03-20 21:19 ` Eric W. Biederman
2007-03-23 0:51 ` Herbert Poetzl
2007-03-23 5:57 ` Nick Piggin
2007-03-23 10:12 ` Eric W. Biederman
2007-03-23 10:47 ` Nick Piggin
2007-03-23 12:21 ` Eric W. Biederman
2007-03-28 7:33 ` Nick Piggin
2007-03-23 16:41 ` Dave Hansen
2007-03-23 18:16 ` Herbert Poetzl
2007-03-28 9:18 ` Balbir Singh
2007-03-14 16:47 ` [RFC][PATCH 2/7] RSS controller core Mel Gorman
2007-03-07 5:37 ` Balbir Singh
2007-03-07 7:27 ` Pavel Emelianov
2007-03-06 14:58 ` [RFC][PATCH 3/7] Data structures changes for RSS accounting Pavel Emelianov
2007-03-11 19:13 ` Eric W. Biederman
2007-03-12 16:16 ` Kirill Korotaev
2007-03-12 16:48 ` Dave Hansen
2007-03-12 17:19 ` Pavel Emelianov
2007-03-12 17:27 ` Dave Hansen
2007-03-13 7:10 ` Pavel Emelianov
2007-03-12 17:21 ` Balbir Singh
2007-03-06 15:00 ` [RFC][PATCH 4/7] RSS accounting hooks over the code Pavel Emelianov
2007-03-11 19:14 ` Eric W. Biederman
2007-03-12 16:23 ` Kirill Korotaev
2007-03-12 16:50 ` Dave Hansen
2007-03-12 17:07 ` Kirill Korotaev
2007-03-12 17:33 ` Dave Hansen
2007-03-13 9:43 ` Eric W. Biederman
2007-03-12 23:54 ` Herbert Poetzl
2007-03-13 9:58 ` Eric W. Biederman
2007-03-13 10:25 ` Nick Piggin
2007-03-13 16:01 ` Eric W. Biederman
2007-03-14 3:51 ` Nick Piggin
2007-03-14 6:42 ` Balbir Singh
2007-03-14 6:57 ` Nick Piggin
2007-03-14 7:48 ` Balbir Singh
2007-03-14 13:25 ` Vaidyanathan Srinivasan
2007-03-14 13:49 ` Nick Piggin
2007-03-14 14:43 ` Vaidyanathan Srinivasan
2007-03-14 16:16 ` Kirill Korotaev
2007-03-15 5:01 ` Nick Piggin
2007-03-15 5:44 ` Balbir Singh
2007-03-28 20:15 ` Ethan Solomita
2007-03-14 15:37 ` Cedric Le Goater
2007-03-14 15:45 ` Pavel Emelianov
2007-03-06 15:03 ` [RFC][PATCH 5/7] Per-container OOM killer and page reclamation Pavel Emelianov
2007-03-09 21:21 ` Balbir Singh
2007-03-11 8:41 ` Pavel Emelianov
2007-03-06 15:04 ` [RFC][PATCH 6/7] Account for the number of tasks within container Pavel Emelianov
2007-03-07 2:00 ` Paul Menage
2007-03-07 7:13 ` Pavel Emelianov
2007-03-08 13:49 ` Paul Menage
2007-03-11 8:36 ` Pavel Emelianov
2007-03-06 15:07 ` [RFC][PATCH 7/7] Account for the number of files opened " Pavel Emelianov
2007-03-07 2:02 ` [RFC][PATCH 0/7] Resource controllers based on process containers Paul Menage
2007-03-07 7:30 ` Pavel Emelianov
2007-03-07 6:52 ` Balbir Singh
2007-03-07 7:32 ` Pavel Emelianov
2007-03-07 9:43 ` Kirill Korotaev
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=45ED80E1.7030406@sw.ru \
--to=xemul@sw.ru \
--cc=akpm@osdl.org \
--cc=balbir@in.ibm.com \
--cc=containers@lists.osdl.org \
--cc=dev@sw.ru \
--cc=devel@openvz.org \
--cc=linux-kernel@vger.kernel.org \
--cc=menage@google.com \
--cc=vatsa@in.ibm.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).