From: root@programming.kicks-ass.net
To: linux-mm@kvack.org, linux-kernel@vger.kernel.org
Cc: miklos@szeredi.hu, akpm@linux-foundation.org, neilb@suse.de,
dgc@sgi.com, tomoki.sekiyama.qu@hitachi.com,
a.p.zijlstra@chello.nl, nikita@clusterfs.com
Subject: [PATCH 10/12] mm: page_alloc_wait
Date: Thu, 05 Apr 2007 19:42:19 +0200 [thread overview]
Message-ID: <20070405174320.129577639@programming.kicks-ass.net> (raw)
In-Reply-To: 20070405174209.498059336@programming.kicks-ass.net
[-- Attachment #1: page_alloc_wait.patch --]
[-- Type: text/plain, Size: 4689 bytes --]
Introduce a mechanism to wait on free memory.
Currently congestion_wait() is abused to do this.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
arch/i386/lib/usercopy.c | 2 +-
fs/xfs/linux-2.6/kmem.c | 4 ++--
include/linux/mm.h | 3 +++
mm/page_alloc.c | 25 +++++++++++++++++++++++--
mm/shmem.c | 2 +-
mm/vmscan.c | 1 +
6 files changed, 31 insertions(+), 6 deletions(-)
Index: linux-2.6-mm/arch/i386/lib/usercopy.c
===================================================================
--- linux-2.6-mm.orig/arch/i386/lib/usercopy.c 2007-04-05 16:24:15.000000000 +0200
+++ linux-2.6-mm/arch/i386/lib/usercopy.c 2007-04-05 16:29:49.000000000 +0200
@@ -751,7 +751,7 @@ survive:
if (retval == -ENOMEM && is_init(current)) {
up_read(¤t->mm->mmap_sem);
- congestion_wait(WRITE, HZ/50);
+ page_alloc_wait(HZ/50);
goto survive;
}
Index: linux-2.6-mm/fs/xfs/linux-2.6/kmem.c
===================================================================
--- linux-2.6-mm.orig/fs/xfs/linux-2.6/kmem.c 2007-04-05 16:24:15.000000000 +0200
+++ linux-2.6-mm/fs/xfs/linux-2.6/kmem.c 2007-04-05 16:29:49.000000000 +0200
@@ -53,7 +53,7 @@ kmem_alloc(size_t size, unsigned int __n
printk(KERN_ERR "XFS: possible memory allocation "
"deadlock in %s (mode:0x%x)\n",
__FUNCTION__, lflags);
- congestion_wait(WRITE, HZ/50);
+ page_alloc_wait(HZ/50);
} while (1);
}
@@ -131,7 +131,7 @@ kmem_zone_alloc(kmem_zone_t *zone, unsig
printk(KERN_ERR "XFS: possible memory allocation "
"deadlock in %s (mode:0x%x)\n",
__FUNCTION__, lflags);
- congestion_wait(WRITE, HZ/50);
+ page_alloc_wait(HZ/50);
} while (1);
}
Index: linux-2.6-mm/include/linux/mm.h
===================================================================
--- linux-2.6-mm.orig/include/linux/mm.h 2007-04-05 16:24:15.000000000 +0200
+++ linux-2.6-mm/include/linux/mm.h 2007-04-05 16:29:49.000000000 +0200
@@ -1028,6 +1028,9 @@ extern void setup_per_cpu_pageset(void);
static inline void setup_per_cpu_pageset(void) {}
#endif
+void page_alloc_ok(void);
+long page_alloc_wait(long timeout);
+
/* prio_tree.c */
void vma_prio_tree_add(struct vm_area_struct *, struct vm_area_struct *old);
void vma_prio_tree_insert(struct vm_area_struct *, struct prio_tree_root *);
Index: linux-2.6-mm/mm/page_alloc.c
===================================================================
--- linux-2.6-mm.orig/mm/page_alloc.c 2007-04-05 16:24:15.000000000 +0200
+++ linux-2.6-mm/mm/page_alloc.c 2007-04-05 16:35:04.000000000 +0200
@@ -107,6 +107,9 @@ unsigned long __meminitdata nr_kernel_pa
unsigned long __meminitdata nr_all_pages;
static unsigned long __initdata dma_reserve;
+static wait_queue_head_t page_alloc_wqh =
+ __WAIT_QUEUE_HEAD_INITIALIZER(page_alloc_wqh);
+
#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
/*
* MAX_ACTIVE_REGIONS determines the maxmimum number of distinct
@@ -1698,7 +1701,7 @@ nofail_alloc:
if (page)
goto got_pg;
if (gfp_mask & __GFP_NOFAIL) {
- congestion_wait(WRITE, HZ/50);
+ page_alloc_wait(HZ/50);
goto nofail_alloc;
}
}
@@ -1763,7 +1766,7 @@ nofail_alloc:
do_retry = 1;
}
if (do_retry) {
- congestion_wait(WRITE, HZ/50);
+ page_alloc_wait(HZ/50);
goto rebalance;
}
@@ -4217,3 +4220,21 @@ void set_pageblock_flags_group(struct pa
else
__clear_bit(bitidx + start_bitidx, bitmap);
}
+
+void page_alloc_ok(void)
+{
+ if (waitqueue_active(&page_alloc_wqh))
+ wake_up(&page_alloc_wqh);
+}
+
+long page_alloc_wait(long timeout)
+{
+ long ret;
+ DEFINE_WAIT(wait);
+
+ prepare_to_wait(&page_alloc_wqh, &wait, TASK_UNINTERRUPTIBLE);
+ ret = schedule_timeout(timeout);
+ finish_wait(&page_alloc_wqh, &wait);
+ return ret;
+}
+EXPORT_SYMBOL(page_alloc_wait);
Index: linux-2.6-mm/mm/shmem.c
===================================================================
--- linux-2.6-mm.orig/mm/shmem.c 2007-04-05 16:24:15.000000000 +0200
+++ linux-2.6-mm/mm/shmem.c 2007-04-05 16:30:31.000000000 +0200
@@ -1216,7 +1216,7 @@ repeat:
page_cache_release(swappage);
if (error == -ENOMEM) {
/* let kswapd refresh zone for GFP_ATOMICs */
- congestion_wait(WRITE, HZ/50);
+ page_alloc_wait(HZ/50);
}
goto repeat;
}
Index: linux-2.6-mm/mm/vmscan.c
===================================================================
--- linux-2.6-mm.orig/mm/vmscan.c 2007-04-05 16:29:46.000000000 +0200
+++ linux-2.6-mm/mm/vmscan.c 2007-04-05 16:29:49.000000000 +0200
@@ -1436,6 +1436,7 @@ static int kswapd(void *p)
finish_wait(&pgdat->kswapd_wait, &wait);
balance_pgdat(pgdat, order);
+ page_alloc_ok();
}
return 0;
}
--
WARNING: multiple messages have this Message-ID (diff)
From: root@programming.kicks-ass.net
To: linux-mm@kvack.org, linux-kernel@vger.kernel.org
Cc: miklos@szeredi.hu, akpm@linux-foundation.org, neilb@suse.de,
dgc@sgi.com, tomoki.sekiyama.qu@hitachi.com,
a.p.zijlstra@chello.nl, nikita@clusterfs.com
Subject: [PATCH 10/12] mm: page_alloc_wait
Date: Thu, 05 Apr 2007 19:42:19 +0200 [thread overview]
Message-ID: <20070405174320.129577639@programming.kicks-ass.net> (raw)
In-Reply-To: 20070405174209.498059336@programming.kicks-ass.net
[-- Attachment #1: page_alloc_wait.patch --]
[-- Type: text/plain, Size: 4914 bytes --]
Introduce a mechanism to wait on free memory.
Currently congestion_wait() is abused to do this.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
arch/i386/lib/usercopy.c | 2 +-
fs/xfs/linux-2.6/kmem.c | 4 ++--
include/linux/mm.h | 3 +++
mm/page_alloc.c | 25 +++++++++++++++++++++++--
mm/shmem.c | 2 +-
mm/vmscan.c | 1 +
6 files changed, 31 insertions(+), 6 deletions(-)
Index: linux-2.6-mm/arch/i386/lib/usercopy.c
===================================================================
--- linux-2.6-mm.orig/arch/i386/lib/usercopy.c 2007-04-05 16:24:15.000000000 +0200
+++ linux-2.6-mm/arch/i386/lib/usercopy.c 2007-04-05 16:29:49.000000000 +0200
@@ -751,7 +751,7 @@ survive:
if (retval == -ENOMEM && is_init(current)) {
up_read(¤t->mm->mmap_sem);
- congestion_wait(WRITE, HZ/50);
+ page_alloc_wait(HZ/50);
goto survive;
}
Index: linux-2.6-mm/fs/xfs/linux-2.6/kmem.c
===================================================================
--- linux-2.6-mm.orig/fs/xfs/linux-2.6/kmem.c 2007-04-05 16:24:15.000000000 +0200
+++ linux-2.6-mm/fs/xfs/linux-2.6/kmem.c 2007-04-05 16:29:49.000000000 +0200
@@ -53,7 +53,7 @@ kmem_alloc(size_t size, unsigned int __n
printk(KERN_ERR "XFS: possible memory allocation "
"deadlock in %s (mode:0x%x)\n",
__FUNCTION__, lflags);
- congestion_wait(WRITE, HZ/50);
+ page_alloc_wait(HZ/50);
} while (1);
}
@@ -131,7 +131,7 @@ kmem_zone_alloc(kmem_zone_t *zone, unsig
printk(KERN_ERR "XFS: possible memory allocation "
"deadlock in %s (mode:0x%x)\n",
__FUNCTION__, lflags);
- congestion_wait(WRITE, HZ/50);
+ page_alloc_wait(HZ/50);
} while (1);
}
Index: linux-2.6-mm/include/linux/mm.h
===================================================================
--- linux-2.6-mm.orig/include/linux/mm.h 2007-04-05 16:24:15.000000000 +0200
+++ linux-2.6-mm/include/linux/mm.h 2007-04-05 16:29:49.000000000 +0200
@@ -1028,6 +1028,9 @@ extern void setup_per_cpu_pageset(void);
static inline void setup_per_cpu_pageset(void) {}
#endif
+void page_alloc_ok(void);
+long page_alloc_wait(long timeout);
+
/* prio_tree.c */
void vma_prio_tree_add(struct vm_area_struct *, struct vm_area_struct *old);
void vma_prio_tree_insert(struct vm_area_struct *, struct prio_tree_root *);
Index: linux-2.6-mm/mm/page_alloc.c
===================================================================
--- linux-2.6-mm.orig/mm/page_alloc.c 2007-04-05 16:24:15.000000000 +0200
+++ linux-2.6-mm/mm/page_alloc.c 2007-04-05 16:35:04.000000000 +0200
@@ -107,6 +107,9 @@ unsigned long __meminitdata nr_kernel_pa
unsigned long __meminitdata nr_all_pages;
static unsigned long __initdata dma_reserve;
+static wait_queue_head_t page_alloc_wqh =
+ __WAIT_QUEUE_HEAD_INITIALIZER(page_alloc_wqh);
+
#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
/*
* MAX_ACTIVE_REGIONS determines the maxmimum number of distinct
@@ -1698,7 +1701,7 @@ nofail_alloc:
if (page)
goto got_pg;
if (gfp_mask & __GFP_NOFAIL) {
- congestion_wait(WRITE, HZ/50);
+ page_alloc_wait(HZ/50);
goto nofail_alloc;
}
}
@@ -1763,7 +1766,7 @@ nofail_alloc:
do_retry = 1;
}
if (do_retry) {
- congestion_wait(WRITE, HZ/50);
+ page_alloc_wait(HZ/50);
goto rebalance;
}
@@ -4217,3 +4220,21 @@ void set_pageblock_flags_group(struct pa
else
__clear_bit(bitidx + start_bitidx, bitmap);
}
+
+void page_alloc_ok(void)
+{
+ if (waitqueue_active(&page_alloc_wqh))
+ wake_up(&page_alloc_wqh);
+}
+
+long page_alloc_wait(long timeout)
+{
+ long ret;
+ DEFINE_WAIT(wait);
+
+ prepare_to_wait(&page_alloc_wqh, &wait, TASK_UNINTERRUPTIBLE);
+ ret = schedule_timeout(timeout);
+ finish_wait(&page_alloc_wqh, &wait);
+ return ret;
+}
+EXPORT_SYMBOL(page_alloc_wait);
Index: linux-2.6-mm/mm/shmem.c
===================================================================
--- linux-2.6-mm.orig/mm/shmem.c 2007-04-05 16:24:15.000000000 +0200
+++ linux-2.6-mm/mm/shmem.c 2007-04-05 16:30:31.000000000 +0200
@@ -1216,7 +1216,7 @@ repeat:
page_cache_release(swappage);
if (error == -ENOMEM) {
/* let kswapd refresh zone for GFP_ATOMICs */
- congestion_wait(WRITE, HZ/50);
+ page_alloc_wait(HZ/50);
}
goto repeat;
}
Index: linux-2.6-mm/mm/vmscan.c
===================================================================
--- linux-2.6-mm.orig/mm/vmscan.c 2007-04-05 16:29:46.000000000 +0200
+++ linux-2.6-mm/mm/vmscan.c 2007-04-05 16:29:49.000000000 +0200
@@ -1436,6 +1436,7 @@ static int kswapd(void *p)
finish_wait(&pgdat->kswapd_wait, &wait);
balance_pgdat(pgdat, order);
+ page_alloc_ok();
}
return 0;
}
--
--
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:[~2007-04-05 18:03 UTC|newest]
Thread overview: 54+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-04-05 17:42 [PATCH 00/12] per device dirty throttling -v3 root
2007-04-05 17:42 ` root
2007-04-05 17:42 ` [PATCH 01/12] nfs: remove congestion_end() root
2007-04-05 17:42 ` root
2007-04-05 17:42 ` [PATCH 02/12] mm: scalable bdi statistics counters root
2007-04-05 17:42 ` root
2007-04-05 22:37 ` Andrew Morton
2007-04-05 22:37 ` Andrew Morton
2007-04-06 7:22 ` Peter Zijlstra
2007-04-06 7:22 ` Peter Zijlstra
2007-04-05 17:42 ` [PATCH 03/12] mm: count dirty pages per BDI root
2007-04-05 17:42 ` root
2007-04-05 17:42 ` [PATCH 04/12] mm: count writeback " root
2007-04-05 17:42 ` root
2007-04-05 17:42 ` [PATCH 05/12] mm: count unstable " root
2007-04-05 17:42 ` root
2007-04-05 17:42 ` [PATCH 06/12] mm: expose BDI statistics in sysfs root
2007-04-05 17:42 ` root
2007-04-05 17:42 ` [PATCH 07/12] mm: per device dirty threshold root
2007-04-05 17:42 ` root
2007-04-05 17:42 ` [PATCH 08/12] mm: fixup possible deadlock root
2007-04-05 17:42 ` root
2007-04-05 22:43 ` Andrew Morton
2007-04-05 22:43 ` Andrew Morton
2007-04-05 17:42 ` [PATCH 09/12] mm: remove throttle_vm_writeback root
2007-04-05 17:42 ` root
2007-04-05 22:44 ` Andrew Morton
2007-04-05 22:44 ` Andrew Morton
2007-09-26 20:42 ` Peter Zijlstra
2007-09-26 20:42 ` Peter Zijlstra
2007-04-05 17:42 ` root [this message]
2007-04-05 17:42 ` [PATCH 10/12] mm: page_alloc_wait root
2007-04-05 22:57 ` Andrew Morton
2007-04-05 22:57 ` Andrew Morton
2007-04-06 6:37 ` Peter Zijlstra
2007-04-06 6:37 ` Peter Zijlstra
2007-04-05 17:42 ` [PATCH 11/12] mm: accurate pageout congestion wait root
2007-04-05 17:42 ` root
2007-04-05 23:17 ` Andrew Morton
2007-04-05 23:17 ` Andrew Morton
2007-04-06 6:51 ` Peter Zijlstra
2007-04-06 6:51 ` Peter Zijlstra
2007-04-05 17:42 ` [PATCH 12/12] mm: per BDI congestion feedback root
2007-04-05 17:42 ` root
2007-04-05 23:24 ` Andrew Morton
2007-04-05 23:24 ` Andrew Morton
2007-04-06 7:01 ` Peter Zijlstra
2007-04-06 7:01 ` Peter Zijlstra
2007-04-06 11:00 ` Andrew Morton
2007-04-06 11:00 ` Andrew Morton
2007-04-06 11:10 ` Miklos Szeredi
2007-04-06 11:10 ` Miklos Szeredi
2007-04-05 17:47 ` [PATCH 00/12] per device dirty throttling -v3 Peter Zijlstra
2007-04-05 17:47 ` Peter Zijlstra
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=20070405174320.129577639@programming.kicks-ass.net \
--to=root@programming.kicks-ass.net \
--cc=a.p.zijlstra@chello.nl \
--cc=akpm@linux-foundation.org \
--cc=dgc@sgi.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=miklos@szeredi.hu \
--cc=neilb@suse.de \
--cc=nikita@clusterfs.com \
--cc=tomoki.sekiyama.qu@hitachi.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 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.