public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Paul Menage <menage@google.com>
To: akpm@linuxfoundation.org, balbir@linux.vnet.ibm.com,
	"Serge E. Hallyn" <serue@us.ibm.com>,
	Cedric Le Goater <clg@fr.ibm.com>,
	"Eric W. Biederman" <ebiederm@xmission.com>,
	Pavel Emelianov <xemul@openvz.org>,
	David Rientjes <rientjes@google.com>,
	Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>,
	Peter Zijlstra <a.p.zijlstra@chello.nl>,
	pj@sgi.com, containers@lists.osdl.org,
	linux-kernel@vger.kernel.org
Subject: [PATCH 21/33] memory controller resource counters v7
Date: Mon, 17 Sep 2007 14:03:28 -0700	[thread overview]
Message-ID: <20070917210429.524831000@menage.corp.google.com> (raw)
In-Reply-To: 20070917210307.116234000@menage.corp.google.com

[-- Attachment #1: memory-controller-resource-counters-v7.patch --]
[-- Type: text/plain, Size: 7174 bytes --]

From: Pavel Emelianov <xemul@openvz.org>
(container->cgroup renaming by Paul Menage <menage@google.com>)

Introduce generic structures and routines for resource accounting.

Each resource accounting cgroup is supposed to aggregate it,
cgroup_subsystem_state and its resource-specific members within.

Signed-off-by: Pavel Emelianov <xemul@openvz.org>
Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Signed-off-by: Paul Menage <menage@google.com>
---

 include/linux/res_counter.h |  102 ++++++++++++++++++++++++++++
 init/Kconfig                |    7 +
 kernel/Makefile             |    1 
 kernel/res_counter.c        |  120 ++++++++++++++++++++++++++++++++++
 4 files changed, 230 insertions(+)

diff -puN /dev/null include/linux/res_counter.h
--- /dev/null
+++ a/include/linux/res_counter.h
@@ -0,0 +1,102 @@
+#ifndef __RES_COUNTER_H__
+#define __RES_COUNTER_H__
+
+/*
+ * Resource Counters
+ * Contain common data types and routines for resource accounting
+ *
+ * Copyright 2007 OpenVZ SWsoft Inc
+ *
+ * Author: Pavel Emelianov <xemul@openvz.org>
+ *
+ */
+
+#include <linux/cgroup.h>
+
+/*
+ * The core object. the cgroup that wishes to account for some
+ * resource may include this counter into its structures and use
+ * the helpers described beyond
+ */
+
+struct res_counter {
+	/*
+	 * the current resource consumption level
+	 */
+	unsigned long usage;
+	/*
+	 * the limit that usage cannot exceed
+	 */
+	unsigned long limit;
+	/*
+	 * the number of unsuccessful attempts to consume the resource
+	 */
+	unsigned long failcnt;
+	/*
+	 * the lock to protect all of the above.
+	 * the routines below consider this to be IRQ-safe
+	 */
+	spinlock_t lock;
+};
+
+/*
+ * Helpers to interact with userspace
+ * res_counter_read/_write - put/get the specified fields from the
+ * res_counter struct to/from the user
+ *
+ * @counter:     the counter in question
+ * @member:  the field to work with (see RES_xxx below)
+ * @buf:     the buffer to opeate on,...
+ * @nbytes:  its size...
+ * @pos:     and the offset.
+ */
+
+ssize_t res_counter_read(struct res_counter *counter, int member,
+		const char __user *buf, size_t nbytes, loff_t *pos);
+ssize_t res_counter_write(struct res_counter *counter, int member,
+		const char __user *buf, size_t nbytes, loff_t *pos);
+
+/*
+ * the field descriptors. one for each member of res_counter
+ */
+
+enum {
+	RES_USAGE,
+	RES_LIMIT,
+	RES_FAILCNT,
+};
+
+/*
+ * helpers for accounting
+ */
+
+void res_counter_init(struct res_counter *counter);
+
+/*
+ * charge - try to consume more resource.
+ *
+ * @counter: the counter
+ * @val: the amount of the resource. each controller defines its own
+ *       units, e.g. numbers, bytes, Kbytes, etc
+ *
+ * returns 0 on success and <0 if the counter->usage will exceed the
+ * counter->limit _locked call expects the counter->lock to be taken
+ */
+
+int res_counter_charge_locked(struct res_counter *counter, unsigned long val);
+int res_counter_charge(struct res_counter *counter, unsigned long val);
+
+/*
+ * uncharge - tell that some portion of the resource is released
+ *
+ * @counter: the counter
+ * @val: the amount of the resource
+ *
+ * these calls check for usage underflow and show a warning on the console
+ * _locked call expects the counter->lock to be taken
+ */
+
+void res_counter_uncharge_locked(struct res_counter *counter, unsigned long val);
+void res_counter_uncharge(struct res_counter *counter, unsigned long val);
+
+#endif
diff -puN init/Kconfig~memory-controller-resource-counters-v7 init/Kconfig
--- a/init/Kconfig~memory-controller-resource-counters-v7
+++ a/init/Kconfig
@@ -319,6 +319,13 @@ config CPUSETS
 
 	  Say N if unsure.
 
+config RESOURCE_COUNTERS
+	bool "Resource counters"
+	help
+	  This option enables controller independent resource accounting
+          infrastructure that works with cgroups
+	depends on CGROUPS
+
 config SYSFS_DEPRECATED
 	bool "Create deprecated sysfs files"
 	default y
diff -puN kernel/Makefile~memory-controller-resource-counters-v7 kernel/Makefile
--- a/kernel/Makefile~memory-controller-resource-counters-v7
+++ a/kernel/Makefile
@@ -59,6 +59,7 @@ obj-$(CONFIG_RELAY) += relay.o
 obj-$(CONFIG_SYSCTL) += utsname_sysctl.o
 obj-$(CONFIG_TASK_DELAY_ACCT) += delayacct.o
 obj-$(CONFIG_TASKSTATS) += taskstats.o tsacct.o
+obj-$(CONFIG_RESOURCE_COUNTERS) += res_counter.o
 
 ifneq ($(CONFIG_SCHED_NO_NO_OMIT_FRAME_POINTER),y)
 # According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is
diff -puN /dev/null kernel/res_counter.c
--- /dev/null
+++ a/kernel/res_counter.c
@@ -0,0 +1,120 @@
+/*
+ * resource cgroups
+ *
+ * Copyright 2007 OpenVZ SWsoft Inc
+ *
+ * Author: Pavel Emelianov <xemul@openvz.org>
+ *
+ */
+
+#include <linux/types.h>
+#include <linux/parser.h>
+#include <linux/fs.h>
+#include <linux/res_counter.h>
+#include <linux/uaccess.h>
+
+void res_counter_init(struct res_counter *counter)
+{
+	spin_lock_init(&counter->lock);
+	counter->limit = (unsigned long)LONG_MAX;
+}
+
+int res_counter_charge_locked(struct res_counter *counter, unsigned long val)
+{
+	if (counter->usage > (counter->limit - val)) {
+		counter->failcnt++;
+		return -ENOMEM;
+	}
+
+	counter->usage += val;
+	return 0;
+}
+
+int res_counter_charge(struct res_counter *counter, unsigned long val)
+{
+	int ret;
+	unsigned long flags;
+
+	spin_lock_irqsave(&counter->lock, flags);
+	ret = res_counter_charge_locked(counter, val);
+	spin_unlock_irqrestore(&counter->lock, flags);
+	return ret;
+}
+
+void res_counter_uncharge_locked(struct res_counter *counter, unsigned long val)
+{
+	if (WARN_ON(counter->usage < val))
+		val = counter->usage;
+
+	counter->usage -= val;
+}
+
+void res_counter_uncharge(struct res_counter *counter, unsigned long val)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&counter->lock, flags);
+	res_counter_uncharge_locked(counter, val);
+	spin_unlock_irqrestore(&counter->lock, flags);
+}
+
+
+static inline unsigned long *res_counter_member(struct res_counter *counter,
+						int member)
+{
+	switch (member) {
+	case RES_USAGE:
+		return &counter->usage;
+	case RES_LIMIT:
+		return &counter->limit;
+	case RES_FAILCNT:
+		return &counter->failcnt;
+	};
+
+	BUG();
+	return NULL;
+}
+
+ssize_t res_counter_read(struct res_counter *counter, int member,
+		const char __user *userbuf, size_t nbytes, loff_t *pos)
+{
+	unsigned long *val;
+	char buf[64], *s;
+
+	s = buf;
+	val = res_counter_member(counter, member);
+	s += sprintf(s, "%lu\n", *val);
+	return simple_read_from_buffer((void __user *)userbuf, nbytes,
+			pos, buf, s - buf);
+}
+
+ssize_t res_counter_write(struct res_counter *counter, int member,
+		const char __user *userbuf, size_t nbytes, loff_t *pos)
+{
+	int ret;
+	char *buf, *end;
+	unsigned long tmp, *val;
+
+	buf = kmalloc(nbytes + 1, GFP_KERNEL);
+	ret = -ENOMEM;
+	if (buf == NULL)
+		goto out;
+
+	buf[nbytes] = '\0';
+	ret = -EFAULT;
+	if (copy_from_user(buf, userbuf, nbytes))
+		goto out_free;
+
+	ret = -EINVAL;
+	tmp = simple_strtoul(buf, &end, 10);
+	if (*end != '\0')
+		goto out_free;
+
+	val = res_counter_member(counter, member);
+	*val = tmp;
+	ret = nbytes;
+out_free:
+	kfree(buf);
+out:
+	return ret;
+}
_

--

  parent reply	other threads:[~2007-09-17 21:11 UTC|newest]

Thread overview: 46+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2007-09-17 21:03 [PATCH 00/33] Rename "Task Containers" to "Control Groups" Paul Menage
2007-09-17 21:03 ` [PATCH 01/33] task containersv11 basic task container framework Paul Menage
2007-09-17 21:03 ` [PATCH 02/33] task containersv11 basic task container framework fix Paul Menage
2007-09-17 21:03 ` [PATCH 03/33] task containersv11 add tasks file interface Paul Menage
2007-10-03  8:09   ` Paul Jackson
2007-10-03 15:16     ` Paul Menage
2007-10-03 17:51       ` Paul Jackson
2007-10-03 18:15         ` Paul Menage
2007-10-04  2:46       ` Paul Jackson
2007-10-04  2:53         ` Paul Menage
2007-10-04  2:55     ` Paul Jackson
2007-09-17 21:03 ` [PATCH 04/33] task containersv11 add fork exit hooks Paul Menage
2007-09-17 21:03 ` [PATCH 05/33] task containersv11 add container_clone interface Paul Menage
2007-09-17 21:03 ` [PATCH 06/33] task containersv11 add procfs interface Paul Menage
2007-09-17 21:03 ` [PATCH 07/33] task containersv11 shared container subsystem group arrays Paul Menage
2007-09-17 21:03 ` [PATCH 08/33] task containersv11 shared container subsystem group arrays avoid lockdep warning Paul Menage
2007-09-17 21:03 ` [PATCH 09/33] task containersv11 shared container subsystem group arrays include fix Paul Menage
2007-09-17 21:03 ` [PATCH 10/33] task containersv11 automatic userspace notification of idle containers Paul Menage
2007-09-17 21:03 ` [PATCH 11/33] task containersv11 make cpusets a client of containers Paul Menage
2007-10-04  9:53   ` Paul Jackson
2007-10-04 15:16     ` Paul Menage
2007-10-04 17:31       ` Paul Jackson
2007-10-04 17:32       ` Paul Jackson
2007-09-17 21:03 ` [PATCH 12/33] task containersv11 example cpu accounting subsystem Paul Menage
2007-09-17 21:03 ` [PATCH 13/33] task containersv11 simple task container debug info subsystem Paul Menage
2007-09-17 21:03 ` [PATCH 14/33] task-containersv11-basic-task-container-framework-containers-fix-refcount-bug Paul Menage
2007-09-17 21:03 ` [PATCH 15/33] task-containersv11-add-container_clone-interface-cgroups-fix-refcount-bug Paul Menage
2007-09-17 21:03 ` [PATCH 16/33] add containerstats v3 Paul Menage
2007-09-17 21:03 ` [PATCH 17/33] add containerstats v3 fix Paul Menage
2007-09-17 21:03 ` [PATCH 18/33] containers implement namespace tracking subsystem Paul Menage
2007-09-17 21:03 ` [PATCH 19/33] containers implement namespace tracking subsystem fix order of container subsystems in init kconfig Paul Menage
2007-09-17 21:03 ` [PATCH 20/33] memory controller add documentation Paul Menage
2007-09-18 16:53   ` Randy Dunlap
2007-09-17 21:03 ` Paul Menage [this message]
2007-09-17 21:03 ` [PATCH 22/33] memory controller resource counters v7 fix Paul Menage
2007-09-17 21:03 ` [PATCH 23/33] memory controller containers setup v7 Paul Menage
2007-09-17 21:03 ` [PATCH 24/33] memory controller accounting " Paul Menage
2007-09-17 21:03 ` [PATCH 25/33] memory controller memory accounting v7 Paul Menage
2007-09-17 21:03 ` [PATCH 26/33] memory controller task migration v7 Paul Menage
2007-09-17 21:03 ` [PATCH 27/33] memory controller add per container lru and reclaim v7 Paul Menage
2007-09-17 21:03 ` [PATCH 28/33] memory controller add per container lru and reclaim v7 fix Paul Menage
2007-09-17 21:03 ` [PATCH 29/33] memory controller oom handling v7 Paul Menage
2007-09-17 21:03 ` [PATCH 30/33] memory controller add switch to control what type of pages to limit v7 Paul Menage
2007-09-17 21:03 ` [PATCH 31/33] memory controller make page_referenced container aware v7 Paul Menage
2007-09-17 21:03 ` [PATCH 32/33] memory-controller-improve-user-interface Paul Menage
2007-09-17 21:03 ` [PATCH 33/33] memory-controller-make-charging-gfp-mask-aware Paul Menage

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=20070917210429.524831000@menage.corp.google.com \
    --to=menage@google.com \
    --cc=a.p.zijlstra@chello.nl \
    --cc=akpm@linuxfoundation.org \
    --cc=balbir@linux.vnet.ibm.com \
    --cc=clg@fr.ibm.com \
    --cc=containers@lists.osdl.org \
    --cc=ebiederm@xmission.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=nickpiggin@yahoo.com.au \
    --cc=pj@sgi.com \
    --cc=rientjes@google.com \
    --cc=serue@us.ibm.com \
    --cc=svaidy@linux.vnet.ibm.com \
    --cc=xemul@openvz.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox