LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: "Aubrey Li" <aubreylee@gmail.com>
To: linux-kernel@vger.kernel.org, linux-mm@kvack.org
Cc: "Linus Torvalds" <torvalds@osdl.org>,
"Andrew Morton" <akpm@osdl.org>,
"Nick Piggin" <nickpiggin@yahoo.com.au>,
"linux-os (Dick Johnson)" <linux-os@analogic.com>,
"Robin Getz" <rgetz@blackfin.uclinux.org>
Subject: [RPC][PATCH 2.6.20-rc5] limit total vfs page cache
Date: Thu, 18 Jan 2007 11:23:23 +0800 [thread overview]
Message-ID: <6d6a94c50701171923g48c8652ayd281a10d1cb5dd95@mail.gmail.com> (raw)
[-- Attachment #1: Type: text/plain, Size: 4731 bytes --]
Here is the newest patch against 2.6.20-rc5.
======================================================
>From ad9ca9a32bdcaddce9988afbf0187bfd04685a0c Mon Sep 17 00:00:00 2001
From: Aubrey.Li <aubreylee@gmail.com>
Date: Thu, 18 Jan 2007 11:08:31 +0800
Subject: [PATCH] Add an interface to limit total vfs page cache.
The default percent is using 90% memory for page cache.
Signed-off-by: Aubrey.Li <aubreylee@gmail.com>
---
include/linux/gfp.h | 1 +
include/linux/pagemap.h | 2 +-
include/linux/sysctl.h | 2 ++
kernel/sysctl.c | 11 +++++++++++
mm/page_alloc.c | 17 +++++++++++++++--
5 files changed, 30 insertions(+), 3 deletions(-)
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 00c314a..531360e 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -46,6 +46,7 @@ struct vm_area_struct;
#define __GFP_NOMEMALLOC ((__force gfp_t)0x10000u) /* Don't use
emergency reserves */
#define __GFP_HARDWALL ((__force gfp_t)0x20000u) /* Enforce
hardwall cpuset memory allocs */
#define __GFP_THISNODE ((__force gfp_t)0x40000u)/* No fallback, no policies */
+#define __GFP_PAGECACHE ((__force gfp_t)0x80000u) /* Is page cache
allocation ? */
#define __GFP_BITS_SHIFT 20 /* Room for 20 __GFP_FOO bits */
#define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1))
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index c3e255b..890bb23 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -62,7 +62,7 @@ static inline struct page *__page_cache_
static inline struct page *page_cache_alloc(struct address_space *x)
{
- return __page_cache_alloc(mapping_gfp_mask(x));
+ return __page_cache_alloc(mapping_gfp_mask(x)|__GFP_PAGECACHE);
}
static inline struct page *page_cache_alloc_cold(struct address_space *x)
diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index 81480e6..d3c9174 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -202,6 +202,7 @@ enum
VM_PANIC_ON_OOM=33, /* panic at out-of-memory */
VM_VDSO_ENABLED=34, /* map VDSO into new processes? */
VM_MIN_SLAB=35, /* Percent pages ignored by zone reclaim */
+ VM_PAGECACHE_RATIO=36, /* percent of RAM to use as page cache */
};
@@ -955,6 +956,7 @@ extern ctl_handler sysctl_string;
extern ctl_handler sysctl_intvec;
extern ctl_handler sysctl_jiffies;
extern ctl_handler sysctl_ms_jiffies;
+extern int sysctl_pagecache_ratio;
/*
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 600b333..92db115 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1035,6 +1035,17 @@ static ctl_table vm_table[] = {
.extra1 = &zero,
},
#endif
+ {
+ .ctl_name = VM_PAGECACHE_RATIO,
+ .procname = "pagecache_ratio",
+ .data = &sysctl_pagecache_ratio,
+ .maxlen = sizeof(sysctl_pagecache_ratio),
+ .mode = 0644,
+ .proc_handler = &proc_dointvec_minmax,
+ .strategy = &sysctl_intvec,
+ .extra1 = &zero,
+ .extra2 = &one_hundred,
+ },
{ .ctl_name = 0 }
};
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index fc5b544..5802b39 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -82,6 +82,8 @@ int sysctl_lowmem_reserve_ratio[MAX_NR_Z
#endif
};
+int sysctl_pagecache_ratio = 10;
+
EXPORT_SYMBOL(totalram_pages);
static char * const zone_names[MAX_NR_ZONES] = {
@@ -895,6 +897,7 @@ failed:
#define ALLOC_HARDER 0x10 /* try to alloc harder */
#define ALLOC_HIGH 0x20 /* __GFP_HIGH set */
#define ALLOC_CPUSET 0x40 /* check for correct cpuset */
+#define ALLOC_PAGECACHE 0x80 /* __GFP_PAGECACHE set */
#ifdef CONFIG_FAIL_PAGE_ALLOC
@@ -998,6 +1001,9 @@ int zone_watermark_ok(struct zone *z, in
if (alloc_flags & ALLOC_HARDER)
min -= min / 4;
+ if (alloc_flags & ALLOC_PAGECACHE)
+ min = min + (sysctl_pagecache_ratio * z->present_pages) / 100;
+
if (free_pages <= min + z->lowmem_reserve[classzone_idx])
return 0;
for (o = 0; o < order; o++) {
@@ -1236,8 +1242,12 @@ restart:
return NULL;
}
- page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, order,
- zonelist, ALLOC_WMARK_LOW|ALLOC_CPUSET);
+ if (gfp_mask & __GFP_PAGECACHE)
+ page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, order,
+ zonelist, ALLOC_WMARK_LOW|ALLOC_CPUSET|ALLOC_PAGECACHE);
+ else
+ page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, order,
+ zonelist, ALLOC_WMARK_LOW|ALLOC_CPUSET);
if (page)
goto got_pg;
@@ -1273,6 +1283,9 @@ restart:
if (wait)
alloc_flags |= ALLOC_CPUSET;
+ if (gfp_mask & __GFP_PAGECACHE)
+ alloc_flags |= ALLOC_PAGECACHE;
+
/*
* Go through the zonelist again. Let __GFP_HIGH and allocations
* coming from realtime tasks go deeper into reserves.
--
1.4.3.4
=====================================================
[-- Attachment #2: 0001-Add-an-interface-to-limit-total-vfs-page-cache.txt --]
[-- Type: text/plain, Size: 4593 bytes --]
From ad9ca9a32bdcaddce9988afbf0187bfd04685a0c Mon Sep 17 00:00:00 2001
From: Aubrey.Li <aubreylee@gmail.com>
Date: Thu, 18 Jan 2007 11:08:31 +0800
Subject: [PATCH] Add an interface to limit total vfs page cache.
The default percent is using 90% memory for page cache.
Signed-off-by: Aubrey.Li <aubreylee@gmail.com>
---
include/linux/gfp.h | 1 +
include/linux/pagemap.h | 2 +-
include/linux/sysctl.h | 2 ++
kernel/sysctl.c | 11 +++++++++++
mm/page_alloc.c | 17 +++++++++++++++--
5 files changed, 30 insertions(+), 3 deletions(-)
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 00c314a..531360e 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -46,6 +46,7 @@ struct vm_area_struct;
#define __GFP_NOMEMALLOC ((__force gfp_t)0x10000u) /* Don't use emergency reserves */
#define __GFP_HARDWALL ((__force gfp_t)0x20000u) /* Enforce hardwall cpuset memory allocs */
#define __GFP_THISNODE ((__force gfp_t)0x40000u)/* No fallback, no policies */
+#define __GFP_PAGECACHE ((__force gfp_t)0x80000u) /* Is page cache allocation ? */
#define __GFP_BITS_SHIFT 20 /* Room for 20 __GFP_FOO bits */
#define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1))
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index c3e255b..890bb23 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -62,7 +62,7 @@ static inline struct page *__page_cache_
static inline struct page *page_cache_alloc(struct address_space *x)
{
- return __page_cache_alloc(mapping_gfp_mask(x));
+ return __page_cache_alloc(mapping_gfp_mask(x)|__GFP_PAGECACHE);
}
static inline struct page *page_cache_alloc_cold(struct address_space *x)
diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index 81480e6..d3c9174 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -202,6 +202,7 @@ enum
VM_PANIC_ON_OOM=33, /* panic at out-of-memory */
VM_VDSO_ENABLED=34, /* map VDSO into new processes? */
VM_MIN_SLAB=35, /* Percent pages ignored by zone reclaim */
+ VM_PAGECACHE_RATIO=36, /* percent of RAM to use as page cache */
};
@@ -955,6 +956,7 @@ extern ctl_handler sysctl_string;
extern ctl_handler sysctl_intvec;
extern ctl_handler sysctl_jiffies;
extern ctl_handler sysctl_ms_jiffies;
+extern int sysctl_pagecache_ratio;
/*
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 600b333..92db115 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1035,6 +1035,17 @@ static ctl_table vm_table[] = {
.extra1 = &zero,
},
#endif
+ {
+ .ctl_name = VM_PAGECACHE_RATIO,
+ .procname = "pagecache_ratio",
+ .data = &sysctl_pagecache_ratio,
+ .maxlen = sizeof(sysctl_pagecache_ratio),
+ .mode = 0644,
+ .proc_handler = &proc_dointvec_minmax,
+ .strategy = &sysctl_intvec,
+ .extra1 = &zero,
+ .extra2 = &one_hundred,
+ },
{ .ctl_name = 0 }
};
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index fc5b544..5802b39 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -82,6 +82,8 @@ int sysctl_lowmem_reserve_ratio[MAX_NR_Z
#endif
};
+int sysctl_pagecache_ratio = 10;
+
EXPORT_SYMBOL(totalram_pages);
static char * const zone_names[MAX_NR_ZONES] = {
@@ -895,6 +897,7 @@ failed:
#define ALLOC_HARDER 0x10 /* try to alloc harder */
#define ALLOC_HIGH 0x20 /* __GFP_HIGH set */
#define ALLOC_CPUSET 0x40 /* check for correct cpuset */
+#define ALLOC_PAGECACHE 0x80 /* __GFP_PAGECACHE set */
#ifdef CONFIG_FAIL_PAGE_ALLOC
@@ -998,6 +1001,9 @@ int zone_watermark_ok(struct zone *z, in
if (alloc_flags & ALLOC_HARDER)
min -= min / 4;
+ if (alloc_flags & ALLOC_PAGECACHE)
+ min = min + (sysctl_pagecache_ratio * z->present_pages) / 100;
+
if (free_pages <= min + z->lowmem_reserve[classzone_idx])
return 0;
for (o = 0; o < order; o++) {
@@ -1236,8 +1242,12 @@ restart:
return NULL;
}
- page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, order,
- zonelist, ALLOC_WMARK_LOW|ALLOC_CPUSET);
+ if (gfp_mask & __GFP_PAGECACHE)
+ page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, order,
+ zonelist, ALLOC_WMARK_LOW|ALLOC_CPUSET|ALLOC_PAGECACHE);
+ else
+ page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, order,
+ zonelist, ALLOC_WMARK_LOW|ALLOC_CPUSET);
if (page)
goto got_pg;
@@ -1273,6 +1283,9 @@ restart:
if (wait)
alloc_flags |= ALLOC_CPUSET;
+ if (gfp_mask & __GFP_PAGECACHE)
+ alloc_flags |= ALLOC_PAGECACHE;
+
/*
* Go through the zonelist again. Let __GFP_HIGH and allocations
* coming from realtime tasks go deeper into reserves.
--
1.4.3.4
next reply other threads:[~2007-01-18 3:23 UTC|newest]
Thread overview: 20+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-01-18 3:23 Aubrey Li [this message]
2007-01-19 14:44 ` [RPC][PATCH 2.6.20-rc5] limit total vfs page cache Vaidyanathan Srinivasan
2007-01-19 15:40 ` Aubrey Li
2007-01-24 5:30 ` Vaidyanathan Srinivasan
2007-01-24 5:53 ` Aubrey Li
2007-01-19 14:52 ` Vaidyanathan Srinivasan
2007-01-19 16:05 ` Aubrey Li
2007-01-19 18:49 ` Vaidyanathan Srinivasan
2007-01-19 19:01 ` Christoph Lameter
2007-01-20 2:04 ` Aubrey Li
2007-01-20 2:24 ` Nick Piggin
2007-01-20 2:35 ` Mike Frysinger
2007-01-20 2:49 ` Nick Piggin
2007-01-20 3:40 ` Mike Frysinger
2007-01-20 3:08 ` Aubrey Li
2007-01-20 4:03 ` Nick Piggin
2007-01-20 4:26 ` Aubrey Li
2007-01-22 19:22 ` Christoph Lameter
2007-01-22 19:15 ` Christoph Lameter
2007-01-19 18:21 ` Christoph Lameter
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=6d6a94c50701171923g48c8652ayd281a10d1cb5dd95@mail.gmail.com \
--to=aubreylee@gmail.com \
--cc=akpm@osdl.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-os@analogic.com \
--cc=nickpiggin@yahoo.com.au \
--cc=rgetz@blackfin.uclinux.org \
--cc=torvalds@osdl.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;
as well as URLs for NNTP newsgroup(s).