From: Magnus Damm <magnus@valinux.co.jp>
To: Linux Kernel <linux-kernel@vger.kernel.org>, linux-mm@kvack.org
Cc: Magnus Damm <magnus@valinux.co.jp>
Subject: [PATCH 03/03] Unmapped: Add guarantee code
Date: Fri, 10 Mar 2006 12:44:25 +0900 (JST) [thread overview]
Message-ID: <20060310034429.8340.61997.sendpatchset@cherry.local> (raw)
In-Reply-To: <20060310034412.8340.90939.sendpatchset@cherry.local>
Implement per-LRU guarantee through sysctl.
This patch introduces the two new sysctl files "node_mapped_guar" and
"node_unmapped_guar". Each file contains one percentage per node and tells
the system how many percentage of all pages that should be kept in RAM as
unmapped or mapped pages.
Signed-off-by: Magnus Damm <magnus@valinux.co.jp>
---
include/linux/mmzone.h | 7 ++++
include/linux/sysctl.h | 2 +
kernel/sysctl.c | 18 ++++++++++++
mm/vmscan.c | 68 ++++++++++++++++++++++++++++++++++++++++++++++++
4 files changed, 95 insertions(+)
--- from-0003/include/linux/mmzone.h
+++ to-work/include/linux/mmzone.h 2006-03-06 18:07:22.000000000 +0900
@@ -124,6 +124,7 @@ struct lru {
unsigned long nr_inactive;
unsigned long nr_scan_active;
unsigned long nr_scan_inactive;
+ unsigned long nr_guaranteed;
};
#define LRU_MAPPED 0
@@ -459,6 +460,12 @@ int lowmem_reserve_ratio_sysctl_handler(
void __user *, size_t *, loff_t *);
int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *, int, struct file *,
void __user *, size_t *, loff_t *);
+extern int sysctl_node_mapped_guar[MAX_NUMNODES];
+int node_mapped_guar_sysctl_handler(struct ctl_table *, int, struct file *,
+ void __user *, size_t *, loff_t *);
+extern int sysctl_node_unmapped_guar[MAX_NUMNODES];
+int node_unmapped_guar_sysctl_handler(struct ctl_table *, int, struct file *,
+ void __user *, size_t *, loff_t *);
#include <linux/topology.h>
/* Returns the number of the current Node. */
--- from-0002/include/linux/sysctl.h
+++ to-work/include/linux/sysctl.h 2006-03-06 18:07:22.000000000 +0900
@@ -185,6 +185,8 @@ enum
VM_PERCPU_PAGELIST_FRACTION=30,/* int: fraction of pages in each percpu_pagelist */
VM_ZONE_RECLAIM_MODE=31, /* reclaim local zone memory before going off node */
VM_ZONE_RECLAIM_INTERVAL=32, /* time period to wait after reclaim failure */
+ VM_NODE_MAPPED_GUAR=33, /* percent of node memory guaranteed mapped */
+ VM_NODE_UNMAPPED_GUAR=34, /* percent of node memory guaranteed unmapped */
};
--- from-0002/kernel/sysctl.c
+++ to-work/kernel/sysctl.c 2006-03-06 18:07:22.000000000 +0900
@@ -899,6 +899,24 @@ static ctl_table vm_table[] = {
.strategy = &sysctl_jiffies,
},
#endif
+ {
+ .ctl_name = VM_NODE_MAPPED_GUAR,
+ .procname = "node_mapped_guar",
+ .data = &sysctl_node_mapped_guar,
+ .maxlen = sizeof(sysctl_node_mapped_guar),
+ .mode = 0644,
+ .proc_handler = &node_mapped_guar_sysctl_handler,
+ .strategy = &sysctl_intvec,
+ },
+ {
+ .ctl_name = VM_NODE_UNMAPPED_GUAR,
+ .procname = "node_unmapped_guar",
+ .data = &sysctl_node_unmapped_guar,
+ .maxlen = sizeof(sysctl_node_unmapped_guar),
+ .mode = 0644,
+ .proc_handler = &node_unmapped_guar_sysctl_handler,
+ .strategy = &sysctl_intvec,
+ },
{ .ctl_name = 0 }
};
--- from-0004/mm/vmscan.c
+++ to-work/mm/vmscan.c 2006-03-06 18:07:22.000000000 +0900
@@ -29,6 +29,7 @@
#include <linux/backing-dev.h>
#include <linux/rmap.h>
#include <linux/topology.h>
+#include <linux/sysctl.h>
#include <linux/cpu.h>
#include <linux/cpuset.h>
#include <linux/notifier.h>
@@ -1284,6 +1285,11 @@ shrink_lru(struct zone *zone, int lru_nr
unsigned long nr_active;
unsigned long nr_inactive;
+ /* No need to scan if guarantee is not fulfilled */
+
+ if ((lru->nr_active + lru->nr_inactive) <= lru->nr_guaranteed)
+ return;
+
atomic_inc(&zone->reclaim_in_progress);
/*
@@ -1325,6 +1331,68 @@ shrink_lru(struct zone *zone, int lru_nr
atomic_dec(&zone->reclaim_in_progress);
}
+spinlock_t sysctl_node_guar_lock = SPIN_LOCK_UNLOCKED;
+int sysctl_node_mapped_guar[MAX_NUMNODES];
+int sysctl_node_mapped_guar_ok[MAX_NUMNODES];
+int sysctl_node_unmapped_guar[MAX_NUMNODES];
+int sysctl_node_unmapped_guar_ok[MAX_NUMNODES];
+
+static void setup_per_lru_guarantee(int lru_nr)
+{
+ struct zone *zone;
+ unsigned long nr;
+ int nid, i;
+
+ for_each_zone(zone) {
+ nid = zone->zone_pgdat->node_id;
+
+ if ((sysctl_node_mapped_guar[nid] +
+ sysctl_node_unmapped_guar[nid]) > 100) {
+ if (lru_nr == LRU_MAPPED) {
+ i = sysctl_node_mapped_guar_ok[nid];
+ sysctl_node_mapped_guar[nid] = i;
+ }
+ else {
+ i = sysctl_node_unmapped_guar_ok[nid];
+ sysctl_node_unmapped_guar[nid] = i;
+ }
+ }
+
+ if (lru_nr == LRU_MAPPED) {
+ i = sysctl_node_mapped_guar[nid];
+ sysctl_node_mapped_guar_ok[nid] = i;
+ }
+ else {
+ i = sysctl_node_unmapped_guar[nid];
+ sysctl_node_unmapped_guar_ok[nid] = i;
+ }
+
+ nr = zone->present_pages - zone->pages_high;
+
+ zone->lru[lru_nr].nr_guaranteed = (nr * i) / 100;
+ }
+}
+
+int node_mapped_guar_sysctl_handler(ctl_table *table, int write,
+ struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
+{
+ spin_lock(&sysctl_node_guar_lock);
+ proc_dointvec_minmax(table, write, file, buffer, length, ppos);
+ setup_per_lru_guarantee(LRU_MAPPED);
+ spin_unlock(&sysctl_node_guar_lock);
+ return 0;
+}
+
+int node_unmapped_guar_sysctl_handler(ctl_table *table, int write,
+ struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
+{
+ spin_lock(&sysctl_node_guar_lock);
+ proc_dointvec_minmax(table, write, file, buffer, length, ppos);
+ setup_per_lru_guarantee(LRU_UNMAPPED);
+ spin_unlock(&sysctl_node_guar_lock);
+ return 0;
+}
+
/*
* This is a basic per-zone page freer. Used by both kswapd and direct reclaim.
*/
WARNING: multiple messages have this Message-ID (diff)
From: Magnus Damm <magnus@valinux.co.jp>
To: Linux Kernel <linux-kernel@vger.kernel.org>, linux-mm@kvack.org
Cc: Magnus Damm <magnus@valinux.co.jp>
Subject: [PATCH 03/03] Unmapped: Add guarantee code
Date: Fri, 10 Mar 2006 12:44:25 +0900 (JST) [thread overview]
Message-ID: <20060310034429.8340.61997.sendpatchset@cherry.local> (raw)
In-Reply-To: <20060310034412.8340.90939.sendpatchset@cherry.local>
Implement per-LRU guarantee through sysctl.
This patch introduces the two new sysctl files "node_mapped_guar" and
"node_unmapped_guar". Each file contains one percentage per node and tells
the system how many percentage of all pages that should be kept in RAM as
unmapped or mapped pages.
Signed-off-by: Magnus Damm <magnus@valinux.co.jp>
---
include/linux/mmzone.h | 7 ++++
include/linux/sysctl.h | 2 +
kernel/sysctl.c | 18 ++++++++++++
mm/vmscan.c | 68 ++++++++++++++++++++++++++++++++++++++++++++++++
4 files changed, 95 insertions(+)
--- from-0003/include/linux/mmzone.h
+++ to-work/include/linux/mmzone.h 2006-03-06 18:07:22.000000000 +0900
@@ -124,6 +124,7 @@ struct lru {
unsigned long nr_inactive;
unsigned long nr_scan_active;
unsigned long nr_scan_inactive;
+ unsigned long nr_guaranteed;
};
#define LRU_MAPPED 0
@@ -459,6 +460,12 @@ int lowmem_reserve_ratio_sysctl_handler(
void __user *, size_t *, loff_t *);
int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *, int, struct file *,
void __user *, size_t *, loff_t *);
+extern int sysctl_node_mapped_guar[MAX_NUMNODES];
+int node_mapped_guar_sysctl_handler(struct ctl_table *, int, struct file *,
+ void __user *, size_t *, loff_t *);
+extern int sysctl_node_unmapped_guar[MAX_NUMNODES];
+int node_unmapped_guar_sysctl_handler(struct ctl_table *, int, struct file *,
+ void __user *, size_t *, loff_t *);
#include <linux/topology.h>
/* Returns the number of the current Node. */
--- from-0002/include/linux/sysctl.h
+++ to-work/include/linux/sysctl.h 2006-03-06 18:07:22.000000000 +0900
@@ -185,6 +185,8 @@ enum
VM_PERCPU_PAGELIST_FRACTION=30,/* int: fraction of pages in each percpu_pagelist */
VM_ZONE_RECLAIM_MODE=31, /* reclaim local zone memory before going off node */
VM_ZONE_RECLAIM_INTERVAL=32, /* time period to wait after reclaim failure */
+ VM_NODE_MAPPED_GUAR=33, /* percent of node memory guaranteed mapped */
+ VM_NODE_UNMAPPED_GUAR=34, /* percent of node memory guaranteed unmapped */
};
--- from-0002/kernel/sysctl.c
+++ to-work/kernel/sysctl.c 2006-03-06 18:07:22.000000000 +0900
@@ -899,6 +899,24 @@ static ctl_table vm_table[] = {
.strategy = &sysctl_jiffies,
},
#endif
+ {
+ .ctl_name = VM_NODE_MAPPED_GUAR,
+ .procname = "node_mapped_guar",
+ .data = &sysctl_node_mapped_guar,
+ .maxlen = sizeof(sysctl_node_mapped_guar),
+ .mode = 0644,
+ .proc_handler = &node_mapped_guar_sysctl_handler,
+ .strategy = &sysctl_intvec,
+ },
+ {
+ .ctl_name = VM_NODE_UNMAPPED_GUAR,
+ .procname = "node_unmapped_guar",
+ .data = &sysctl_node_unmapped_guar,
+ .maxlen = sizeof(sysctl_node_unmapped_guar),
+ .mode = 0644,
+ .proc_handler = &node_unmapped_guar_sysctl_handler,
+ .strategy = &sysctl_intvec,
+ },
{ .ctl_name = 0 }
};
--- from-0004/mm/vmscan.c
+++ to-work/mm/vmscan.c 2006-03-06 18:07:22.000000000 +0900
@@ -29,6 +29,7 @@
#include <linux/backing-dev.h>
#include <linux/rmap.h>
#include <linux/topology.h>
+#include <linux/sysctl.h>
#include <linux/cpu.h>
#include <linux/cpuset.h>
#include <linux/notifier.h>
@@ -1284,6 +1285,11 @@ shrink_lru(struct zone *zone, int lru_nr
unsigned long nr_active;
unsigned long nr_inactive;
+ /* No need to scan if guarantee is not fulfilled */
+
+ if ((lru->nr_active + lru->nr_inactive) <= lru->nr_guaranteed)
+ return;
+
atomic_inc(&zone->reclaim_in_progress);
/*
@@ -1325,6 +1331,68 @@ shrink_lru(struct zone *zone, int lru_nr
atomic_dec(&zone->reclaim_in_progress);
}
+spinlock_t sysctl_node_guar_lock = SPIN_LOCK_UNLOCKED;
+int sysctl_node_mapped_guar[MAX_NUMNODES];
+int sysctl_node_mapped_guar_ok[MAX_NUMNODES];
+int sysctl_node_unmapped_guar[MAX_NUMNODES];
+int sysctl_node_unmapped_guar_ok[MAX_NUMNODES];
+
+static void setup_per_lru_guarantee(int lru_nr)
+{
+ struct zone *zone;
+ unsigned long nr;
+ int nid, i;
+
+ for_each_zone(zone) {
+ nid = zone->zone_pgdat->node_id;
+
+ if ((sysctl_node_mapped_guar[nid] +
+ sysctl_node_unmapped_guar[nid]) > 100) {
+ if (lru_nr == LRU_MAPPED) {
+ i = sysctl_node_mapped_guar_ok[nid];
+ sysctl_node_mapped_guar[nid] = i;
+ }
+ else {
+ i = sysctl_node_unmapped_guar_ok[nid];
+ sysctl_node_unmapped_guar[nid] = i;
+ }
+ }
+
+ if (lru_nr == LRU_MAPPED) {
+ i = sysctl_node_mapped_guar[nid];
+ sysctl_node_mapped_guar_ok[nid] = i;
+ }
+ else {
+ i = sysctl_node_unmapped_guar[nid];
+ sysctl_node_unmapped_guar_ok[nid] = i;
+ }
+
+ nr = zone->present_pages - zone->pages_high;
+
+ zone->lru[lru_nr].nr_guaranteed = (nr * i) / 100;
+ }
+}
+
+int node_mapped_guar_sysctl_handler(ctl_table *table, int write,
+ struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
+{
+ spin_lock(&sysctl_node_guar_lock);
+ proc_dointvec_minmax(table, write, file, buffer, length, ppos);
+ setup_per_lru_guarantee(LRU_MAPPED);
+ spin_unlock(&sysctl_node_guar_lock);
+ return 0;
+}
+
+int node_unmapped_guar_sysctl_handler(ctl_table *table, int write,
+ struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
+{
+ spin_lock(&sysctl_node_guar_lock);
+ proc_dointvec_minmax(table, write, file, buffer, length, ppos);
+ setup_per_lru_guarantee(LRU_UNMAPPED);
+ spin_unlock(&sysctl_node_guar_lock);
+ return 0;
+}
+
/*
* This is a basic per-zone page freer. Used by both kswapd and direct reclaim.
*/
--
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 prev parent reply other threads:[~2006-03-10 3:44 UTC|newest]
Thread overview: 50+ messages / expand[flat|nested] mbox.gz Atom feed top
2006-03-10 3:44 [PATCH 00/03] Unmapped: Separate unmapped and mapped pages Magnus Damm
2006-03-10 3:44 ` Magnus Damm
2006-03-10 3:44 ` [PATCH 01/03] Unmapped: Implement two LRU:s Magnus Damm
2006-03-10 3:44 ` Magnus Damm
2006-03-10 19:16 ` Christoph Lameter
2006-03-10 19:16 ` Christoph Lameter
2006-03-11 12:14 ` Magnus Damm
2006-03-11 12:14 ` Magnus Damm
2006-03-10 3:44 ` [PATCH 02/03] Unmapped: Modify LRU behaviour Magnus Damm
2006-03-10 3:44 ` Magnus Damm
2006-03-10 3:44 ` Magnus Damm [this message]
2006-03-10 3:44 ` [PATCH 03/03] Unmapped: Add guarantee code Magnus Damm
2006-03-10 4:57 ` Nick Piggin
2006-03-10 4:57 ` Nick Piggin
2006-03-10 6:04 ` Magnus Damm
2006-03-10 6:04 ` Magnus Damm
2006-03-10 15:41 ` Chandra Seetharaman
2006-03-10 15:41 ` Chandra Seetharaman
2006-03-11 12:29 ` Magnus Damm
2006-03-11 12:29 ` Magnus Damm
2006-03-15 15:32 ` Chandra Seetharaman
2006-03-15 15:32 ` Chandra Seetharaman
2006-03-10 4:55 ` [PATCH 00/03] Unmapped: Separate unmapped and mapped pages Nick Piggin
2006-03-10 4:55 ` Nick Piggin
2006-03-10 5:55 ` Magnus Damm
2006-03-10 5:55 ` Magnus Damm
2006-03-10 7:52 ` Arjan van de Ven
2006-03-10 7:52 ` Arjan van de Ven
2006-03-10 13:19 ` Magnus Damm
2006-03-10 13:19 ` Magnus Damm
2006-03-10 14:05 ` Arjan van de Ven
2006-03-10 14:05 ` Arjan van de Ven
2006-03-11 11:52 ` Magnus Damm
2006-03-11 11:52 ` Magnus Damm
2006-03-11 20:58 ` Peter Zijlstra
2006-03-11 20:58 ` Peter Zijlstra
2006-03-13 2:28 ` Magnus Damm
2006-03-13 2:28 ` Magnus Damm
2006-03-10 12:22 ` Peter Zijlstra
2006-03-10 12:22 ` Peter Zijlstra
2006-03-10 13:38 ` Magnus Damm
2006-03-10 13:38 ` Magnus Damm
2006-03-11 21:08 ` Peter Zijlstra
2006-03-11 21:08 ` Peter Zijlstra
2006-03-13 3:05 ` Magnus Damm
2006-03-13 3:05 ` Magnus Damm
2006-03-10 19:12 ` Christoph Lameter
2006-03-10 19:12 ` Christoph Lameter
2006-03-11 11:56 ` Magnus Damm
2006-03-11 11:56 ` Magnus Damm
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=20060310034429.8340.61997.sendpatchset@cherry.local \
--to=magnus@valinux.co.jp \
--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.