netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Xiaotian Feng <dfeng@redhat.com>
To: linux-mm@kvack.org, linux-nfs@vger.kernel.org, netdev@vger.kernel.org
Cc: riel@redhat.com, cl@linux-foundation.org, a.p.zijlstra@chello.nl,
	Xiaotian Feng <dfeng@redhat.com>,
	linux-kernel@vger.kernel.org, lwang@redhat.com,
	penberg@cs.helsinki.fi, akpm@linux-foundation.org,
	davem@davemloft.net
Subject: [PATCH -mmotm 08/30] mm: emergency pool
Date: Tue, 13 Jul 2010 06:18:21 -0400	[thread overview]
Message-ID: <20100713101821.2835.2568.sendpatchset@danny.redhat> (raw)
In-Reply-To: <20100713101650.2835.15245.sendpatchset@danny.redhat>

>From 973ce2ee797025f055ccb61359180e53c3ecc681 Mon Sep 17 00:00:00 2001
From: Xiaotian Feng <dfeng@redhat.com>
Date: Tue, 13 Jul 2010 10:45:48 +0800
Subject: [PATCH 08/30] mm: emergency pool

Provide means to reserve a specific amount of pages.

The emergency pool is separated from the min watermark because ALLOC_HARDER
and ALLOC_HIGH modify the watermark in a relative way and thus do not ensure
a strict minimum.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Suresh Jayaraman <sjayaraman@suse.de>
Signed-off-by: Xiaotian Feng <dfeng@redhat.com>
---
 include/linux/mmzone.h |    3 ++
 mm/page_alloc.c        |   84 ++++++++++++++++++++++++++++++++++++++++++------
 mm/vmstat.c            |    6 ++--
 3 files changed, 80 insertions(+), 13 deletions(-)

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 9ed9c45..75a0871 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -279,6 +279,7 @@ struct zone_reclaim_stat {
 
 struct zone {
 	/* Fields commonly accessed by the page allocator */
+	unsigned long           pages_emerg;    /* emergency pool */
 
 	/* zone watermarks, access with *_wmark_pages(zone) macros */
 	unsigned long watermark[NR_WMARK];
@@ -770,6 +771,8 @@ int sysctl_min_unmapped_ratio_sysctl_handler(struct ctl_table *, int,
 int sysctl_min_slab_ratio_sysctl_handler(struct ctl_table *, int,
 			void __user *, size_t *, loff_t *);
 
+int adjust_memalloc_reserve(int pages);
+
 extern int numa_zonelist_order_handler(struct ctl_table *, int,
 			void __user *, size_t *, loff_t *);
 extern char numa_zonelist_order[];
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 4b1fa10..6c85e9e 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -167,6 +167,8 @@ static char * const zone_names[MAX_NR_ZONES] = {
 
 static DEFINE_SPINLOCK(min_free_lock);
 int min_free_kbytes = 1024;
+static DEFINE_MUTEX(var_free_mutex);
+int var_free_kbytes;
 
 static unsigned long __meminitdata nr_kernel_pages;
 static unsigned long __meminitdata nr_all_pages;
@@ -1457,7 +1459,7 @@ int zone_watermark_ok(struct zone *z, int order, unsigned long mark,
 	if (alloc_flags & ALLOC_HARDER)
 		min -= min / 4;
 
-	if (free_pages <= min + z->lowmem_reserve[classzone_idx])
+	if (free_pages <= min+z->lowmem_reserve[classzone_idx]+z->pages_emerg)
 		return 0;
 	for (o = 0; o < order; o++) {
 		/* At the next order, this order's pages become unavailable */
@@ -1946,7 +1948,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order,
 {
 	const gfp_t wait = gfp_mask & __GFP_WAIT;
 	struct page *page = NULL;
-	int alloc_flags;
+	int alloc_flags = 0;
 	unsigned long pages_reclaimed = 0;
 	unsigned long did_some_progress;
 	struct task_struct *p = current;
@@ -2078,8 +2080,8 @@ rebalance:
 nopage:
 	if (!(gfp_mask & __GFP_NOWARN) && printk_ratelimit()) {
 		printk(KERN_WARNING "%s: page allocation failure."
-			" order:%d, mode:0x%x\n",
-			p->comm, order, gfp_mask);
+			" order:%d, mode:0x%x, alloc_flags:0x%x, pflags:0x%x\n",
+			p->comm, order, gfp_mask, alloc_flags, p->flags);
 		dump_stack();
 		show_mem();
 	}
@@ -2414,9 +2416,9 @@ void show_free_areas(void)
 			"\n",
 			zone->name,
 			K(zone_page_state(zone, NR_FREE_PAGES)),
-			K(min_wmark_pages(zone)),
-			K(low_wmark_pages(zone)),
-			K(high_wmark_pages(zone)),
+			K(zone->pages_emerg + min_wmark_pages(zone)),
+			K(zone->pages_emerg + low_wmark_pages(zone)),
+			K(zone->pages_emerg + high_wmark_pages(zone)),
 			K(zone_page_state(zone, NR_ACTIVE_ANON)),
 			K(zone_page_state(zone, NR_INACTIVE_ANON)),
 			K(zone_page_state(zone, NR_ACTIVE_FILE)),
@@ -4779,7 +4781,7 @@ static void calculate_totalreserve_pages(void)
 			}
 
 			/* we treat the high watermark as reserved pages. */
-			max += high_wmark_pages(zone);
+			max += high_wmark_pages(zone) + zone->pages_emerg;
 
 			if (max > zone->present_pages)
 				max = zone->present_pages;
@@ -4837,7 +4839,8 @@ static void setup_per_zone_lowmem_reserve(void)
  */
 static void __setup_per_zone_wmarks(void)
 {
-	unsigned long pages_min = min_free_kbytes >> (PAGE_SHIFT - 10);
+	unsigned pages_min = min_free_kbytes >> (PAGE_SHIFT - 10);
+	unsigned pages_emerg = var_free_kbytes >> (PAGE_SHIFT - 10);
 	unsigned long lowmem_pages = 0;
 	struct zone *zone;
 	unsigned long flags;
@@ -4849,11 +4852,13 @@ static void __setup_per_zone_wmarks(void)
 	}
 
 	for_each_zone(zone) {
-		u64 tmp;
+		u64 tmp, tmp_emerg;
 
 		spin_lock_irqsave(&zone->lock, flags);
 		tmp = (u64)pages_min * zone->present_pages;
 		do_div(tmp, lowmem_pages);
+		tmp_emerg = (u64)pages_emerg * zone->present_pages;
+		do_div(tmp_emerg, lowmem_pages);
 		if (is_highmem(zone)) {
 			/*
 			 * __GFP_HIGH and PF_MEMALLOC allocations usually don't
@@ -4872,12 +4877,14 @@ static void __setup_per_zone_wmarks(void)
 			if (min_pages > 128)
 				min_pages = 128;
 			zone->watermark[WMARK_MIN] = min_pages;
+			zone->pages_emerg = 0;
 		} else {
 			/*
 			 * If it's a lowmem zone, reserve a number of pages
 			 * proportionate to the zone's size.
 			 */
 			zone->watermark[WMARK_MIN] = tmp;
+			zone->pages_emerg = tmp_emerg;
 		}
 
 		zone->watermark[WMARK_LOW]  = min_wmark_pages(zone) + (tmp >> 2);
@@ -4942,6 +4949,63 @@ void setup_per_zone_wmarks(void)
 	spin_unlock_irqrestore(&min_free_lock, flags);
 }
 
+static void __adjust_memalloc_reserve(int pages)
+{
+	var_free_kbytes += pages << (PAGE_SHIFT - 10);
+	BUG_ON(var_free_kbytes < 0);
+	setup_per_zone_wmarks();
+}
+
+static int test_reserve_limits(void)
+{
+	struct zone *zone;
+	int node;
+
+	for_each_zone(zone)
+		wakeup_kswapd(zone, 0);
+
+	for_each_online_node(node) {
+		struct page *page = alloc_pages_node(node, GFP_KERNEL, 0);
+		if (!page)
+			return -ENOMEM;
+
+		__free_page(page);
+	}
+
+	return 0;
+}
+
+/**
+ *	adjust_memalloc_reserve - adjust the memalloc reserve
+ *	@pages: number of pages to add
+ *
+ *	It adds a number of pages to the memalloc reserve; if
+ *	the number was positive it kicks reclaim into action to
+ *	satisfy the higher watermarks.
+ *
+ *	returns -ENOMEM when it failed to satisfy the watermarks.
+ */
+int adjust_memalloc_reserve(int pages)
+{
+	int err = 0;
+
+	mutex_lock(&var_free_mutex);
+	__adjust_memalloc_reserve(pages);
+	if (pages > 0) {
+		err = test_reserve_limits();
+		if (err) {
+			__adjust_memalloc_reserve(-pages);
+			goto unlock;
+		}
+	}
+	printk(KERN_DEBUG "Emergency reserve: %d\n", var_free_kbytes);
+
+unlock:
+	mutex_unlock(&var_free_mutex);
+	return err;
+}
+EXPORT_SYMBOL_GPL(adjust_memalloc_reserve);
+
 /*
  * Initialise min_free_kbytes.
  *
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 15a14b1..af91d5c 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -814,9 +814,9 @@ static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat,
 		   "\n        spanned  %lu"
 		   "\n        present  %lu",
 		   zone_page_state(zone, NR_FREE_PAGES),
-		   min_wmark_pages(zone),
-		   low_wmark_pages(zone),
-		   high_wmark_pages(zone),
+		   zone->pages_emerg + min_wmark_pages(zone),
+		   zone->pages_emerg + min_wmark_pages(zone),
+		   zone->pages_emerg + high_wmark_pages(zone),
 		   zone->pages_scanned,
 		   zone->spanned_pages,
 		   zone->present_pages);
-- 
1.7.1.1

--
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:[~2010-07-13 10:18 UTC|newest]

Thread overview: 37+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-07-13 10:16 [PATCH -mmotm 00/30] [RFC] swap over nfs -v21 Xiaotian Feng
2010-07-13 10:17 ` [PATCH -mmotm 01/30] mm: serialize access to min_free_kbytes Xiaotian Feng
2010-07-13 10:17 ` [PATCH -mmotm 02/30] Swap over network documentation Xiaotian Feng
2010-07-13 10:17 ` [PATCH -mmotm 03/30] mm: expose gfp_to_alloc_flags() Xiaotian Feng
2010-07-13 10:17 ` [PATCH -mmotm 04/30] mm: tag reseve pages Xiaotian Feng
2010-07-13 10:17 ` [PATCH -mmotm 05/30] mm: sl[au]b: add knowledge of reserve pages Xiaotian Feng
     [not found]   ` <20100713101747.2835.45722.sendpatchset-bd3XojVv5Xrm7B5McmCzzQ@public.gmane.org>
2010-07-13 20:33     ` Pekka Enberg
2010-07-15 12:37       ` Xiaotian Feng
     [not found]       ` <AANLkTilj5GrhbRJZfSsfXP1v9cQSRlARFmxpys1vUelr-JsoAwUIsXosN+BqQ9rBEUg@public.gmane.org>
2010-08-03  1:44         ` Neil Brown
2010-07-13 10:17 ` [PATCH -mmotm 06/30] mm: kmem_alloc_estimate() Xiaotian Feng
2010-07-13 10:18 ` [PATCH -mmotm 07/30] mm: allow PF_MEMALLOC from softirq context Xiaotian Feng
2010-07-13 10:18 ` Xiaotian Feng [this message]
2010-07-13 10:18 ` [PATCH -mmotm 09/30] mm: system wide ALLOC_NO_WATERMARK Xiaotian Feng
2010-07-13 10:18 ` [PATCH -mmotm 10/30] mm: __GFP_MEMALLOC Xiaotian Feng
2010-07-13 10:18 ` [PATCH -mmotm 11/30] mm: memory reserve management Xiaotian Feng
2010-07-13 10:19 ` [PATCH -mmotm 12/30] selinux: tag avc cache alloc as non-critical Xiaotian Feng
2010-07-13 10:55   ` Mitchell Erblich
2010-07-15 11:51     ` Xiaotian Feng
2010-07-13 10:19 ` [PATCH -mmotm 13/30] net: packet split receive api Xiaotian Feng
2010-07-13 10:19 ` [PATCH -mmotm 14/30] net: sk_allocation() - concentrate socket related allocations Xiaotian Feng
2010-07-13 10:19 ` [PATCH -mmotm 15/30] netvm: network reserve infrastructure Xiaotian Feng
2010-07-13 10:19 ` [PATCH -mmotm 16/30] netvm: INET reserves Xiaotian Feng
2010-07-13 10:20 ` [PATCH -mmotm 17/30] netvm: hook skb allocation to reserves Xiaotian Feng
2010-07-13 10:20 ` [PATCH -mmotm 18/30] netvm: filter emergency skbs Xiaotian Feng
2010-07-13 10:20 ` [PATCH -mmotm 19/30] netvm: prevent a stream specific deadlock Xiaotian Feng
2010-07-13 10:20 ` [PATCH -mmotm 20/30] netfilter: NF_QUEUE vs emergency skbs Xiaotian Feng
2010-07-13 10:20 ` [PATCH -mmotm 21/30] netvm: skb processing Xiaotian Feng
2010-07-13 10:20 ` [PATCH -mmotm 22/30] mm: add support for non block device backed swap files Xiaotian Feng
2010-07-13 10:21 ` [PATCH -mmotm 23/30] mm: methods for teaching filesystems about PG_swapcache pages Xiaotian Feng
2010-07-13 10:21 ` [PATCH -mmotm 24/30] nfs: teach the NFS client how to treat " Xiaotian Feng
2010-07-13 10:21 ` [PATCH -mmotm 25/30] nfs: disable data cache revalidation for swapfiles Xiaotian Feng
2010-07-13 10:21 ` [PATCH -mmotm 26/30] nfs: enable swap on NFS Xiaotian Feng
2010-07-13 10:21 ` [PATCH -mmotm 27/30] nfs: fix various memory recursions possible with swap over NFS Xiaotian Feng
2010-07-13 10:22 ` [PATCH -mmotm 28/30] build fix for skb_emergency_protocol Xiaotian Feng
2010-07-13 10:22 ` [PATCH -mmotm 29/30] fix null pointer deref in swap_entry_free Xiaotian Feng
2010-07-13 10:22 ` [PATCH -mmotm 30/30] fix mess up on swap with multi files from same nfs server Xiaotian Feng
     [not found] ` <20100713101650.2835.15245.sendpatchset-bd3XojVv5Xrm7B5McmCzzQ@public.gmane.org>
2010-07-13 12:53   ` [PATCH -mmotm 00/30] [RFC] swap over nfs -v21 Américo Wang

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=20100713101821.2835.2568.sendpatchset@danny.redhat \
    --to=dfeng@redhat.com \
    --cc=a.p.zijlstra@chello.nl \
    --cc=akpm@linux-foundation.org \
    --cc=cl@linux-foundation.org \
    --cc=davem@davemloft.net \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-nfs@vger.kernel.org \
    --cc=lwang@redhat.com \
    --cc=netdev@vger.kernel.org \
    --cc=penberg@cs.helsinki.fi \
    --cc=riel@redhat.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 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).