All of lore.kernel.org
 help / color / mirror / Atom feed
From: Ethan Solomita <solo@google.com>
To: linux-mm@kvack.org, LKML <linux-kernel@vger.kernel.org>,
	Andrew Morton <akpm@google.com>,
	a.p.zijlstra@chello.nl
Subject: [RFC 7/7] cpuset dirty limits
Date: Thu, 31 May 2007 23:17:35 -0700	[thread overview]
Message-ID: <465FB9FF.4000302@google.com> (raw)
In-Reply-To: <465FB6CF.4090801@google.com>

Per cpuset dirty ratios

This implements dirty ratios per cpuset. Two new files are added
to the cpuset directories:

background_dirty_ratio	Percentage at which background writeback starts

throttle_dirty_ratio	Percentage at which the application is throttled
			and we start synchrononous writeout.

Both variables are set to -1 by default which means that the global
limits (/proc/sys/vm/vm_dirty_ratio and /proc/sys/vm/dirty_background_ratio)
are used for a cpuset.

Originally by Christoph Lameter <clameter@sgi.com>

Signed-off-by: Ethan Solomita <solo@google.com>

---

diff -uprN -X 0/Documentation/dontdiff 6/include/linux/cpuset.h 7/include/linux/cpuset.h
--- 6/include/linux/cpuset.h	2007-05-30 11:39:17.000000000 -0700
+++ 7/include/linux/cpuset.h	2007-05-30 11:39:48.000000000 -0700
@@ -75,6 +75,7 @@ static inline int cpuset_do_slab_mem_spr
 
 extern void cpuset_track_online_nodes(void);
 
+extern void cpuset_get_current_ratios(int *background, int *ratio);
 /*
  * We need macros since struct address_space is not defined yet
  */
diff -uprN -X 0/Documentation/dontdiff 6/kernel/cpuset.c 7/kernel/cpuset.c
--- 6/kernel/cpuset.c	2007-05-30 11:39:17.000000000 -0700
+++ 7/kernel/cpuset.c	2007-05-30 11:39:48.000000000 -0700
@@ -49,6 +49,7 @@
 #include <linux/time.h>
 #include <linux/backing-dev.h>
 #include <linux/sort.h>
+#include <linux/writeback.h>
 
 #include <asm/uaccess.h>
 #include <asm/atomic.h>
@@ -99,6 +100,9 @@ struct cpuset {
 	int mems_generation;
 
 	struct fmeter fmeter;		/* memory_pressure filter */
+
+	int background_dirty_ratio;
+	int throttle_dirty_ratio;
 };
 
 /* bits in struct cpuset flags field */
@@ -176,6 +180,8 @@ static struct cpuset top_cpuset = {
 	.count = ATOMIC_INIT(0),
 	.sibling = LIST_HEAD_INIT(top_cpuset.sibling),
 	.children = LIST_HEAD_INIT(top_cpuset.children),
+	.background_dirty_ratio = -1,
+	.throttle_dirty_ratio = -1,
 };
 
 static struct vfsmount *cpuset_mount;
@@ -1030,6 +1036,21 @@ static int update_flag(cpuset_flagbits_t
 	return 0;
 }
 
+static int update_int(int *cs_int, char *buf, int min, int max)
+{
+	char *endp;
+	int val;
+
+	val = simple_strtol(buf, &endp, 10);
+	if (val < min || val > max)
+		return -EINVAL;
+
+	mutex_lock(&callback_mutex);
+	*cs_int = val;
+	mutex_unlock(&callback_mutex);
+	return 0;
+}
+
 /*
  * Frequency meter - How fast is some event occurring?
  *
@@ -1238,6 +1259,8 @@ typedef enum {
 	FILE_SPREAD_PAGE,
 	FILE_SPREAD_SLAB,
 	FILE_TASKLIST,
+	FILE_THROTTLE_DIRTY_RATIO,
+	FILE_BACKGROUND_DIRTY_RATIO,
 } cpuset_filetype_t;
 
 static ssize_t cpuset_common_file_write(struct file *file,
@@ -1308,6 +1331,12 @@ static ssize_t cpuset_common_file_write(
 	case FILE_TASKLIST:
 		retval = attach_task(cs, buffer, &pathbuf);
 		break;
+	case FILE_BACKGROUND_DIRTY_RATIO:
+		retval = update_int(&cs->background_dirty_ratio, buffer, -1, 100);
+		break;
+	case FILE_THROTTLE_DIRTY_RATIO:
+		retval = update_int(&cs->throttle_dirty_ratio, buffer, -1, 100);
+		break;
 	default:
 		retval = -EINVAL;
 		goto out2;
@@ -1420,6 +1449,12 @@ static ssize_t cpuset_common_file_read(s
 	case FILE_SPREAD_SLAB:
 		*s++ = is_spread_slab(cs) ? '1' : '0';
 		break;
+	case FILE_BACKGROUND_DIRTY_RATIO:
+		s += sprintf(s, "%d", cs->background_dirty_ratio);
+		break;
+	case FILE_THROTTLE_DIRTY_RATIO:
+		s += sprintf(s, "%d", cs->throttle_dirty_ratio);
+		break;
 	default:
 		retval = -EINVAL;
 		goto out;
@@ -1788,6 +1823,16 @@ static struct cftype cft_spread_slab = {
 	.private = FILE_SPREAD_SLAB,
 };
 
+static struct cftype cft_background_dirty_ratio = {
+	.name = "background_dirty_ratio",
+	.private = FILE_BACKGROUND_DIRTY_RATIO,
+};
+
+static struct cftype cft_throttle_dirty_ratio = {
+	.name = "throttle_dirty_ratio",
+	.private = FILE_THROTTLE_DIRTY_RATIO,
+};
+
 static int cpuset_populate_dir(struct dentry *cs_dentry)
 {
 	int err;
@@ -1810,6 +1855,10 @@ static int cpuset_populate_dir(struct de
 		return err;
 	if ((err = cpuset_add_file(cs_dentry, &cft_spread_slab)) < 0)
 		return err;
+	if ((err = cpuset_add_file(cs_dentry, &cft_background_dirty_ratio)) < 0)
+		return err;
+	if ((err = cpuset_add_file(cs_dentry, &cft_throttle_dirty_ratio)) < 0)
+		return err;
 	if ((err = cpuset_add_file(cs_dentry, &cft_tasks)) < 0)
 		return err;
 	return 0;
@@ -1849,6 +1898,8 @@ static long cpuset_create(struct cpuset 
 	INIT_LIST_HEAD(&cs->children);
 	cs->mems_generation = cpuset_mems_generation++;
 	fmeter_init(&cs->fmeter);
+	cs->background_dirty_ratio = parent->background_dirty_ratio;
+	cs->throttle_dirty_ratio = parent->throttle_dirty_ratio;
 
 	cs->parent = parent;
 
@@ -2483,8 +2534,30 @@ int cpuset_mem_spread_node(void)
 }
 EXPORT_SYMBOL_GPL(cpuset_mem_spread_node);
 
-#if MAX_NUMNODES > BITS_PER_LONG
+/*
+ * Determine the dirty ratios for the currently active cpuset
+ */
+void cpuset_get_current_ratios(int *background_ratio, int *throttle_ratio)
+{
+	int background = -1;
+	int throttle = -1;
+	struct task_struct *tsk = current;
+
+	task_lock(tsk);
+	background = tsk->cpuset->background_dirty_ratio;
+	throttle = tsk->cpuset->throttle_dirty_ratio;
+	task_unlock(tsk);
 
+	if (background == -1)
+		background = dirty_background_ratio;
+	if (throttle == -1)
+		throttle = vm_dirty_ratio;
+
+	*background_ratio = background;
+	*throttle_ratio = throttle;
+}
+
+#if MAX_NUMNODES > BITS_PER_LONG
 /*
  * Special functions for NUMA systems with a large number of nodes.
  * The nodemask is pointed to from the address space structures.
diff -uprN -X 0/Documentation/dontdiff 6/mm/page-writeback.c 7/mm/page-writeback.c
--- 6/mm/page-writeback.c	2007-05-30 11:39:25.000000000 -0700
+++ 7/mm/page-writeback.c	2007-05-30 11:39:48.000000000 -0700
@@ -216,6 +216,7 @@ get_dirty_limits(struct dirty_limits *dl
 		}
 		dirtyable_memory -= highmem_dirtyable_memory(nodes,
 							     dirtyable_memory);
+		cpuset_get_current_ratios(&background_ratio, &dirty_ratio);
 	} else
 #endif
 	{
@@ -226,19 +227,19 @@ get_dirty_limits(struct dirty_limits *dl
 		dirtyable_memory = determine_dirtyable_memory();
 		nr_mapped = global_page_state(NR_FILE_MAPPED) +
 			global_page_state(NR_ANON_PAGES);
+		dirty_ratio = vm_dirty_ratio;
+		background_ratio = dirty_background_ratio;
 	}
 
 	unmapped_ratio = 100 - ((global_page_state(NR_FILE_MAPPED) +
 				global_page_state(NR_ANON_PAGES)) * 100) /
 					vm_total_pages;
-	dirty_ratio = vm_dirty_ratio;
 	if (dirty_ratio > unmapped_ratio / 2)
 		dirty_ratio = unmapped_ratio / 2;
 
 	if (dirty_ratio < 5)
 		dirty_ratio = 5;
 
-	background_ratio = dirty_background_ratio;
 	if (background_ratio >= dirty_ratio)
 		background_ratio = dirty_ratio / 2;
 


WARNING: multiple messages have this Message-ID (diff)
From: Ethan Solomita <solo@google.com>
To: linux-mm@kvack.org, LKML <linux-kernel@vger.kernel.org>,
	Andrew Morton <akpm@google.com>,
	a.p.zijlstra@chello.nl
Subject: [RFC 7/7] cpuset dirty limits
Date: Thu, 31 May 2007 23:17:35 -0700	[thread overview]
Message-ID: <465FB9FF.4000302@google.com> (raw)
In-Reply-To: <465FB6CF.4090801@google.com>

Per cpuset dirty ratios

This implements dirty ratios per cpuset. Two new files are added
to the cpuset directories:

background_dirty_ratio	Percentage at which background writeback starts

throttle_dirty_ratio	Percentage at which the application is throttled
			and we start synchrononous writeout.

Both variables are set to -1 by default which means that the global
limits (/proc/sys/vm/vm_dirty_ratio and /proc/sys/vm/dirty_background_ratio)
are used for a cpuset.

Originally by Christoph Lameter <clameter@sgi.com>

Signed-off-by: Ethan Solomita <solo@google.com>

---

diff -uprN -X 0/Documentation/dontdiff 6/include/linux/cpuset.h 7/include/linux/cpuset.h
--- 6/include/linux/cpuset.h	2007-05-30 11:39:17.000000000 -0700
+++ 7/include/linux/cpuset.h	2007-05-30 11:39:48.000000000 -0700
@@ -75,6 +75,7 @@ static inline int cpuset_do_slab_mem_spr
 
 extern void cpuset_track_online_nodes(void);
 
+extern void cpuset_get_current_ratios(int *background, int *ratio);
 /*
  * We need macros since struct address_space is not defined yet
  */
diff -uprN -X 0/Documentation/dontdiff 6/kernel/cpuset.c 7/kernel/cpuset.c
--- 6/kernel/cpuset.c	2007-05-30 11:39:17.000000000 -0700
+++ 7/kernel/cpuset.c	2007-05-30 11:39:48.000000000 -0700
@@ -49,6 +49,7 @@
 #include <linux/time.h>
 #include <linux/backing-dev.h>
 #include <linux/sort.h>
+#include <linux/writeback.h>
 
 #include <asm/uaccess.h>
 #include <asm/atomic.h>
@@ -99,6 +100,9 @@ struct cpuset {
 	int mems_generation;
 
 	struct fmeter fmeter;		/* memory_pressure filter */
+
+	int background_dirty_ratio;
+	int throttle_dirty_ratio;
 };
 
 /* bits in struct cpuset flags field */
@@ -176,6 +180,8 @@ static struct cpuset top_cpuset = {
 	.count = ATOMIC_INIT(0),
 	.sibling = LIST_HEAD_INIT(top_cpuset.sibling),
 	.children = LIST_HEAD_INIT(top_cpuset.children),
+	.background_dirty_ratio = -1,
+	.throttle_dirty_ratio = -1,
 };
 
 static struct vfsmount *cpuset_mount;
@@ -1030,6 +1036,21 @@ static int update_flag(cpuset_flagbits_t
 	return 0;
 }
 
+static int update_int(int *cs_int, char *buf, int min, int max)
+{
+	char *endp;
+	int val;
+
+	val = simple_strtol(buf, &endp, 10);
+	if (val < min || val > max)
+		return -EINVAL;
+
+	mutex_lock(&callback_mutex);
+	*cs_int = val;
+	mutex_unlock(&callback_mutex);
+	return 0;
+}
+
 /*
  * Frequency meter - How fast is some event occurring?
  *
@@ -1238,6 +1259,8 @@ typedef enum {
 	FILE_SPREAD_PAGE,
 	FILE_SPREAD_SLAB,
 	FILE_TASKLIST,
+	FILE_THROTTLE_DIRTY_RATIO,
+	FILE_BACKGROUND_DIRTY_RATIO,
 } cpuset_filetype_t;
 
 static ssize_t cpuset_common_file_write(struct file *file,
@@ -1308,6 +1331,12 @@ static ssize_t cpuset_common_file_write(
 	case FILE_TASKLIST:
 		retval = attach_task(cs, buffer, &pathbuf);
 		break;
+	case FILE_BACKGROUND_DIRTY_RATIO:
+		retval = update_int(&cs->background_dirty_ratio, buffer, -1, 100);
+		break;
+	case FILE_THROTTLE_DIRTY_RATIO:
+		retval = update_int(&cs->throttle_dirty_ratio, buffer, -1, 100);
+		break;
 	default:
 		retval = -EINVAL;
 		goto out2;
@@ -1420,6 +1449,12 @@ static ssize_t cpuset_common_file_read(s
 	case FILE_SPREAD_SLAB:
 		*s++ = is_spread_slab(cs) ? '1' : '0';
 		break;
+	case FILE_BACKGROUND_DIRTY_RATIO:
+		s += sprintf(s, "%d", cs->background_dirty_ratio);
+		break;
+	case FILE_THROTTLE_DIRTY_RATIO:
+		s += sprintf(s, "%d", cs->throttle_dirty_ratio);
+		break;
 	default:
 		retval = -EINVAL;
 		goto out;
@@ -1788,6 +1823,16 @@ static struct cftype cft_spread_slab = {
 	.private = FILE_SPREAD_SLAB,
 };
 
+static struct cftype cft_background_dirty_ratio = {
+	.name = "background_dirty_ratio",
+	.private = FILE_BACKGROUND_DIRTY_RATIO,
+};
+
+static struct cftype cft_throttle_dirty_ratio = {
+	.name = "throttle_dirty_ratio",
+	.private = FILE_THROTTLE_DIRTY_RATIO,
+};
+
 static int cpuset_populate_dir(struct dentry *cs_dentry)
 {
 	int err;
@@ -1810,6 +1855,10 @@ static int cpuset_populate_dir(struct de
 		return err;
 	if ((err = cpuset_add_file(cs_dentry, &cft_spread_slab)) < 0)
 		return err;
+	if ((err = cpuset_add_file(cs_dentry, &cft_background_dirty_ratio)) < 0)
+		return err;
+	if ((err = cpuset_add_file(cs_dentry, &cft_throttle_dirty_ratio)) < 0)
+		return err;
 	if ((err = cpuset_add_file(cs_dentry, &cft_tasks)) < 0)
 		return err;
 	return 0;
@@ -1849,6 +1898,8 @@ static long cpuset_create(struct cpuset 
 	INIT_LIST_HEAD(&cs->children);
 	cs->mems_generation = cpuset_mems_generation++;
 	fmeter_init(&cs->fmeter);
+	cs->background_dirty_ratio = parent->background_dirty_ratio;
+	cs->throttle_dirty_ratio = parent->throttle_dirty_ratio;
 
 	cs->parent = parent;
 
@@ -2483,8 +2534,30 @@ int cpuset_mem_spread_node(void)
 }
 EXPORT_SYMBOL_GPL(cpuset_mem_spread_node);
 
-#if MAX_NUMNODES > BITS_PER_LONG
+/*
+ * Determine the dirty ratios for the currently active cpuset
+ */
+void cpuset_get_current_ratios(int *background_ratio, int *throttle_ratio)
+{
+	int background = -1;
+	int throttle = -1;
+	struct task_struct *tsk = current;
+
+	task_lock(tsk);
+	background = tsk->cpuset->background_dirty_ratio;
+	throttle = tsk->cpuset->throttle_dirty_ratio;
+	task_unlock(tsk);
 
+	if (background == -1)
+		background = dirty_background_ratio;
+	if (throttle == -1)
+		throttle = vm_dirty_ratio;
+
+	*background_ratio = background;
+	*throttle_ratio = throttle;
+}
+
+#if MAX_NUMNODES > BITS_PER_LONG
 /*
  * Special functions for NUMA systems with a large number of nodes.
  * The nodemask is pointed to from the address space structures.
diff -uprN -X 0/Documentation/dontdiff 6/mm/page-writeback.c 7/mm/page-writeback.c
--- 6/mm/page-writeback.c	2007-05-30 11:39:25.000000000 -0700
+++ 7/mm/page-writeback.c	2007-05-30 11:39:48.000000000 -0700
@@ -216,6 +216,7 @@ get_dirty_limits(struct dirty_limits *dl
 		}
 		dirtyable_memory -= highmem_dirtyable_memory(nodes,
 							     dirtyable_memory);
+		cpuset_get_current_ratios(&background_ratio, &dirty_ratio);
 	} else
 #endif
 	{
@@ -226,19 +227,19 @@ get_dirty_limits(struct dirty_limits *dl
 		dirtyable_memory = determine_dirtyable_memory();
 		nr_mapped = global_page_state(NR_FILE_MAPPED) +
 			global_page_state(NR_ANON_PAGES);
+		dirty_ratio = vm_dirty_ratio;
+		background_ratio = dirty_background_ratio;
 	}
 
 	unmapped_ratio = 100 - ((global_page_state(NR_FILE_MAPPED) +
 				global_page_state(NR_ANON_PAGES)) * 100) /
 					vm_total_pages;
-	dirty_ratio = vm_dirty_ratio;
 	if (dirty_ratio > unmapped_ratio / 2)
 		dirty_ratio = unmapped_ratio / 2;
 
 	if (dirty_ratio < 5)
 		dirty_ratio = 5;
 
-	background_ratio = dirty_background_ratio;
 	if (background_ratio >= dirty_ratio)
 		background_ratio = dirty_ratio / 2;
 

--
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>

  parent reply	other threads:[~2007-06-01  6:18 UTC|newest]

Thread overview: 51+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2007-06-01  6:03 [RFC 1/7] cpuset write dirty map Ethan Solomita
2007-06-01  6:03 ` Ethan Solomita
2007-06-01  6:10 ` [RFC 2/7] cpuset write pdflush nodemask Ethan Solomita
2007-06-01  6:10   ` Ethan Solomita
2007-06-01  6:11 ` [RFC 3/7] cpuset write throttle Ethan Solomita
2007-06-01  6:11   ` Ethan Solomita
2007-06-01  6:13 ` [RFC 4/7] cpuset write vmscan Ethan Solomita
2007-06-01  6:13   ` Ethan Solomita
2007-06-01  6:15 ` [RFC 5/7] cpuset write vm writeout Ethan Solomita
2007-06-01  6:15   ` Ethan Solomita
2007-06-01  6:16 ` [corrected][RFC " Ethan Solomita
2007-06-01  6:16   ` Ethan Solomita
2007-06-01  6:16 ` [RFC 6/7] cpuset write fixes Ethan Solomita
2007-06-01  6:16   ` Ethan Solomita
2007-06-01  6:17 ` Ethan Solomita [this message]
2007-06-01  6:17   ` [RFC 7/7] cpuset dirty limits Ethan Solomita
2007-06-04 18:39 ` [RFC 1/7] cpuset write dirty map Christoph Lameter
2007-06-04 18:39   ` Christoph Lameter
2007-06-04 19:38   ` Ethan Solomita
2007-06-04 19:38     ` Ethan Solomita
2007-06-04 19:52     ` Christoph Lameter
2007-06-04 19:52       ` Christoph Lameter
2007-06-25 20:21       ` Ethan Solomita
2007-06-25 20:21         ` Ethan Solomita
2007-06-26 19:16         ` Christoph Lameter
2007-06-26 19:16           ` Christoph Lameter
2007-06-26 22:22           ` Andrew Morton
2007-06-26 22:22             ` Andrew Morton
2007-06-27  3:18             ` Christoph Lameter
2007-06-27  3:18               ` Christoph Lameter
2007-06-27  9:14               ` Andrew Morton
2007-06-27  9:14                 ` Andrew Morton
2007-06-27 12:44                 ` Christoph Lameter
2007-06-27 12:44                   ` Christoph Lameter
2007-06-27 21:10                   ` Mel Gorman
2007-06-27 21:10                     ` Mel Gorman
2007-06-27 18:17             ` Ethan Solomita
2007-06-27 18:17               ` Ethan Solomita
2007-06-27 21:38               ` Christoph Lameter
2007-06-27 21:38                 ` Christoph Lameter
2007-07-01  2:57                 ` Ethan Solomita
2007-07-01  2:57                   ` Ethan Solomita
2007-07-03 18:09                   ` Christoph Lameter
2007-07-03 18:09                     ` Christoph Lameter
2007-07-11 19:18           ` Ethan Solomita
2007-07-11 19:18             ` Ethan Solomita
2007-07-11 20:11             ` Christoph Lameter
2007-07-11 20:11               ` Christoph Lameter
2007-07-12  1:07               ` Ethan Solomita
2007-07-12  1:07                 ` Ethan Solomita
  -- strict thread matches above, loose matches on Subject: below --
2007-04-23 23:20 Ethan Solomita
2007-04-23 23:33 ` [RFC 7/7] cpuset dirty limits Ethan Solomita

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=465FB9FF.4000302@google.com \
    --to=solo@google.com \
    --cc=a.p.zijlstra@chello.nl \
    --cc=akpm@google.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.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.