cpuset write dirty map

diff -uprN -X 0/Documentation/dontdiff 0/fs/buffer.c 1/fs/buffer.c
@@ -41,6 +41,7 @@
 #include <linux/bitops.h>
 #include <linux/mpage.h>
 #include <linux/bit_spinlock.h>
+#include <linux/cpuset.h>
 
 static int fsync_buffers_list(spinlock_t *lock, struct list_head *list);
 

@@ -710,6 +711,7 @@ static int __set_page_dirty(struct page 
 		radix_tree_tag_set(&mapping->page_tree,
 				page_index(page), PAGECACHE_TAG_DIRTY);
 	}
+	cpuset_update_dirty_nodes(mapping, page);
 	write_unlock_irq(&mapping->tree_lock);
 	__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);
 

diff -uprN -X 0/Documentation/dontdiff 0/fs/fs-writeback.c 1/fs/fs-writeback.c
@@ -22,6 +22,7 @@
 #include <linux/blkdev.h>
 #include <linux/backing-dev.h>
 #include <linux/buffer_head.h>
+#include <linux/cpuset.h>
 #include "internal.h"
 
 int sysctl_inode_debug __read_mostly;

@@ -483,6 +484,12 @@ int generic_sync_sb_inodes(struct super_
 			continue;		/* blockdev has wrong queue */
 		}
 
+		if (!cpuset_intersects_dirty_nodes(mapping, wbc->nodes)) {
+			/* No pages on the nodes under writeback */
+			redirty_head(inode);
+			continue;
+		}
+
 		/* Was this inode dirtied after sync_sb_inodes was called? */
 		if (time_after(inode->dirtied_when, start))
 			break;

diff -uprN -X 0/Documentation/dontdiff 0/fs/inode.c 1/fs/inode.c
@@ -22,6 +22,7 @@
 #include <linux/bootmem.h>
 #include <linux/inotify.h>
 #include <linux/mount.h>
+#include <linux/cpuset.h>
 
 /*
  * This is needed for the following functions:

@@ -148,6 +149,7 @@ static struct inode *alloc_inode(struct 
 		mapping_set_gfp_mask(mapping, GFP_HIGHUSER_PAGECACHE);
 		mapping->assoc_mapping = NULL;
 		mapping->backing_dev_info = &default_backing_dev_info;
+		cpuset_init_dirty_nodes(mapping);
 
 		/*
 		 * If the block_device provides a backing_dev_info for client

@@ -255,6 +257,7 @@ void clear_inode(struct inode *inode)
 		bd_forget(inode);
 	if (S_ISCHR(inode->i_mode) && inode->i_cdev)
 		cd_forget(inode);
+	cpuset_clear_dirty_nodes(inode->i_mapping);
 	inode->i_state = I_CLEAR;
 }
 

71 lines not on this page · raw message

diff -uprN -X 0/Documentation/dontdiff 0/include/linux/fs.h 1/include/linux/fs.h
@@ -468,6 +468,13 @@ struct address_space {
 	spinlock_t		private_lock;	/* for use by the address_space */
 	struct list_head	private_list;	/* ditto */
 	struct address_space	*assoc_mapping;	/* ditto */
+#ifdef CONFIG_CPUSETS
+#if MAX_NUMNODES <= BITS_PER_LONG
+	nodemask_t		dirty_nodes;	/* nodes with dirty pages */
+#else
+	nodemask_t		*dirty_nodes;	/* pointer to map if dirty */
+#endif
+#endif
 } __attribute__((aligned(sizeof(long))));
 	/*
 	 * On most architectures that alignment is already the case; but

diff -uprN -X 0/Documentation/dontdiff 0/include/linux/writeback.h 1/include/linux/writeback.h
@@ -63,6 +63,7 @@ struct writeback_control {
 	unsigned range_cyclic:1;	/* range_start is cyclic */
 
 	void *fs_private;		/* For use by ->writepages() */
+	nodemask_t *nodes;		/* Set of nodes of interest */
 };
 
 /*

78 lines not on this page · raw message

diff -uprN -X 0/Documentation/dontdiff 0/mm/page-writeback.c 1/mm/page-writeback.c
@@ -33,6 +33,7 @@
 #include <linux/syscalls.h>
 #include <linux/buffer_head.h>
 #include <linux/pagevec.h>
+#include <linux/cpuset.h>
 
 /*
  * The maximum number of pages to writeout in a single bdflush/kupdate

@@ -834,6 +835,7 @@ int __set_page_dirty_nobuffers(struct pa
 			radix_tree_tag_set(&mapping->page_tree,
 				page_index(page), PAGECACHE_TAG_DIRTY);
 		}
+		cpuset_update_dirty_nodes(mapping, page);
 		write_unlock_irq(&mapping->tree_lock);
 		if (mapping->host) {
 			/* !PageAnon && !swapper_space */

diff -uprN -X 0/Documentation/dontdiff 1/fs/buffer.c 2/fs/buffer.c
@@ -359,7 +359,7 @@ static void free_more_memory(void)
 	struct zone **zones;
 	pg_data_t *pgdat;
 
-	wakeup_pdflush(1024);
+	wakeup_pdflush(1024, NULL);
 	yield();
 
 	for_each_online_pgdat(pgdat) {

diff -uprN -X 0/Documentation/dontdiff 1/fs/super.c 2/fs/super.c
@@ -615,7 +615,7 @@ int do_remount_sb(struct super_block *sb
 	return 0;
 }
 
-static void do_emergency_remount(unsigned long foo)
+static void do_emergency_remount(unsigned long foo, nodemask_t *bar)
 {
 	struct super_block *sb;
 

@@ -643,7 +643,7 @@ static void do_emergency_remount(unsigne
 
 void emergency_remount(void)
 {
-	pdflush_operation(do_emergency_remount, 0);
+	pdflush_operation(do_emergency_remount, 0, NULL);
 }
 
 /*

diff -uprN -X 0/Documentation/dontdiff 1/fs/sync.c 2/fs/sync.c
@@ -21,9 +21,9 @@
  * sync everything.  Start out by waking pdflush, because that writes back
  * all queues in parallel.
  */
-static void do_sync(unsigned long wait)
+static void do_sync(unsigned long wait, nodemask_t *unused)
 {
-	wakeup_pdflush(0);
+	wakeup_pdflush(0, NULL);
 	sync_inodes(0);		/* All mappings, inodes and their blockdevs */
 	DQUOT_SYNC(NULL);
 	sync_supers();		/* Write the superblocks */

@@ -38,13 +38,13 @@ static void do_sync(unsigned long wait)
 
 asmlinkage long sys_sync(void)
 {
-	do_sync(1);
+	do_sync(1, NULL);
 	return 0;
 }
 
 void emergency_sync(void)
 {
-	pdflush_operation(do_sync, 0);
+	pdflush_operation(do_sync, 0, NULL);
 }
 
 /*

diff -uprN -X 0/Documentation/dontdiff 1/include/linux/writeback.h 2/include/linux/writeback.h
@@ -86,7 +86,7 @@ static inline void wait_on_inode(struct 
 /*
  * mm/page-writeback.c
  */
-int wakeup_pdflush(long nr_pages);
+int wakeup_pdflush(long nr_pages, nodemask_t *nodes);
 void laptop_io_completion(void);
 void laptop_sync_completion(void);
 void throttle_vm_writeout(gfp_t gfp_mask);

@@ -117,7 +117,8 @@ balance_dirty_pages_ratelimited(struct a
 typedef int (*writepage_t)(struct page *page, struct writeback_control *wbc,
 				void *data);
 
-int pdflush_operation(void (*fn)(unsigned long), unsigned long arg0);
+int pdflush_operation(void (*fn)(unsigned long, nodemask_t *nodes),
+			unsigned long arg0, nodemask_t *nodes);
 int generic_writepages(struct address_space *mapping,
 		       struct writeback_control *wbc);
 int write_cache_pages(struct address_space *mapping,

diff -uprN -X 0/Documentation/dontdiff 1/mm/page-writeback.c 2/mm/page-writeback.c
@@ -101,7 +101,7 @@ EXPORT_SYMBOL(laptop_mode);
 /* End of sysctl-exported parameters */
 
 
-static void background_writeout(unsigned long _min_pages);
+static void background_writeout(unsigned long _min_pages, nodemask_t *nodes);
 
 /*
  * Work out the current dirty-memory clamping and background writeout

@@ -272,7 +272,7 @@ static void balance_dirty_pages(struct a
 	 */
 	if ((laptop_mode && pages_written) ||
 	     (!laptop_mode && (nr_reclaimable > background_thresh)))
-		pdflush_operation(background_writeout, 0);
+		pdflush_operation(background_writeout, 0, NULL);
 }
 
 void set_page_dirty_balance(struct page *page)

@@ -362,7 +362,7 @@ void throttle_vm_writeout(gfp_t gfp_mask
  * writeback at least _min_pages, and keep writing until the amount of dirty
  * memory is less than the background threshold, or until we're all clean.
  */
-static void background_writeout(unsigned long _min_pages)
+static void background_writeout(unsigned long _min_pages, nodemask_t *unused)
 {
 	long min_pages = _min_pages;
 	struct writeback_control wbc = {

@@ -402,12 +402,12 @@ static void background_writeout(unsigned
  * the whole world.  Returns 0 if a pdflush thread was dispatched.  Returns
  * -1 if all pdflush threads were busy.
  */
-int wakeup_pdflush(long nr_pages)
+int wakeup_pdflush(long nr_pages, nodemask_t *nodes)
 {
 	if (nr_pages == 0)
 		nr_pages = global_page_state(NR_FILE_DIRTY) +
 				global_page_state(NR_UNSTABLE_NFS);
-	return pdflush_operation(background_writeout, nr_pages);
+	return pdflush_operation(background_writeout, nr_pages, nodes);
 }
 
 static void wb_timer_fn(unsigned long unused);

@@ -431,7 +431,7 @@ static DEFINE_TIMER(laptop_mode_wb_timer
  * older_than_this takes precedence over nr_to_write.  So we'll only write back
  * all dirty pages if they are all attached to "old" mappings.
  */
-static void wb_kupdate(unsigned long arg)
+static void wb_kupdate(unsigned long arg, nodemask_t *unused)
 {
 	unsigned long oldest_jif;
 	unsigned long start_jif;

@@ -491,18 +491,18 @@ int dirty_writeback_centisecs_handler(ct
 
 static void wb_timer_fn(unsigned long unused)
 {
-	if (pdflush_operation(wb_kupdate, 0) < 0)
+	if (pdflush_operation(wb_kupdate, 0, NULL) < 0)
 		mod_timer(&wb_timer, jiffies + HZ); /* delay 1 second */
 }
 
-static void laptop_flush(unsigned long unused)
+static void laptop_flush(unsigned long unused, nodemask_t *unused2)
 {
 	sys_sync();
 }
 
 static void laptop_timer_fn(unsigned long unused)
 {
-	pdflush_operation(laptop_flush, 0);
+	pdflush_operation(laptop_flush, 0, NULL);
 }
 
 /*

diff -uprN -X 0/Documentation/dontdiff 1/mm/pdflush.c 2/mm/pdflush.c
@@ -83,10 +83,12 @@ static unsigned long last_empty_jifs;
  */
 struct pdflush_work {
 	struct task_struct *who;	/* The thread */
-	void (*fn)(unsigned long);	/* A callback function */
+	void (*fn)(unsigned long, nodemask_t *); /* A callback function */
 	unsigned long arg0;		/* An argument to the callback */
 	struct list_head list;		/* On pdflush_list, when idle */
 	unsigned long when_i_went_to_sleep;
+	int have_nodes;			/* Nodes were specified */
+	nodemask_t nodes;		/* Nodes of interest */
 };
 
 static int __pdflush(struct pdflush_work *my_work)

@@ -123,7 +125,8 @@ static int __pdflush(struct pdflush_work
 		}
 		spin_unlock_irq(&pdflush_lock);
 
-		(*my_work->fn)(my_work->arg0);
+		(*my_work->fn)(my_work->arg0,
+			my_work->have_nodes ? &my_work->nodes : NULL);
 
 		/*
 		 * Thread creation: For how long have there been zero

@@ -197,7 +200,8 @@ static int pdflush(void *dummy)
  * Returns zero if it indeed managed to find a worker thread, and passed your
  * payload to it.
  */
-int pdflush_operation(void (*fn)(unsigned long), unsigned long arg0)
+int pdflush_operation(void (*fn)(unsigned long, nodemask_t *),
+			unsigned long arg0, nodemask_t *nodes)
 {
 	unsigned long flags;
 	int ret = 0;

@@ -217,6 +221,11 @@ int pdflush_operation(void (*fn)(unsigne
 			last_empty_jifs = jiffies;
 		pdf->fn = fn;
 		pdf->arg0 = arg0;
+		if (nodes) {
+			pdf->nodes = *nodes;
+			pdf->have_nodes = 1;
+		} else
+			pdf->have_nodes = 0;
 		wake_up_process(pdf->who);
 		spin_unlock_irqrestore(&pdflush_lock, flags);
 	}

diff -uprN -X 0/Documentation/dontdiff 1/mm/vmscan.c 2/mm/vmscan.c
@@ -1198,7 +1198,7 @@ unsigned long try_to_free_pages(struct z
 		 */
 		if (total_scanned > sc.swap_cluster_max +
 					sc.swap_cluster_max / 2) {
-			wakeup_pdflush(laptop_mode ? 0 : total_scanned);
+			wakeup_pdflush(laptop_mode ? 0 : total_scanned, NULL);
 			sc.may_writepage = 1;
 		}
 

diff -uprN -X 0/Documentation/dontdiff 2/mm/page-writeback.c 3/mm/page-writeback.c
@@ -103,6 +103,14 @@ EXPORT_SYMBOL(laptop_mode);
 
 static void background_writeout(unsigned long _min_pages, nodemask_t *nodes);
 
+struct dirty_limits {
+	long thresh_background;
+	long thresh_dirty;
+	unsigned long nr_dirty;
+	unsigned long nr_unstable;
+	unsigned long nr_writeback;
+};
+
 /*
  * Work out the current dirty-memory clamping and background writeout
  * thresholds.

@@ -121,13 +129,15 @@ static void background_writeout(unsigned
  * clamping level.
  */
 
-static unsigned long highmem_dirtyable_memory(unsigned long total)
+static unsigned long highmem_dirtyable_memory(nodemask_t *nodes, unsigned long total)
 {
 #ifdef CONFIG_HIGHMEM
 	int node;
 	unsigned long x = 0;
 
-	for_each_online_node(node) {
+	if (nodes == NULL)
+		nodes = &node_online_mask;
+	for_each_node_mask(node, *nodes) {
 		struct zone *z =
 			&NODE_DATA(node)->node_zones[ZONE_HIGHMEM];
 

@@ -154,13 +164,13 @@ static unsigned long determine_dirtyable
 	x = global_page_state(NR_FREE_PAGES)
 		+ global_page_state(NR_INACTIVE)
 		+ global_page_state(NR_ACTIVE);
-	x -= highmem_dirtyable_memory(x);
+	x -= highmem_dirtyable_memory(NULL, x);
 	return x + 1;	/* Ensure that we never return 0 */
 }
 
-static void
-get_dirty_limits(long *pbackground, long *pdirty,
-					struct address_space *mapping)
+static int
+get_dirty_limits(struct dirty_limits *dl, struct address_space *mapping,
+					nodemask_t *nodes)
 {
 	int background_ratio;		/* Percentages */
 	int dirty_ratio;

@@ -168,12 +178,60 @@ get_dirty_limits(long *pbackground, long
 	long background;
 	long dirty;
 	unsigned long available_memory = determine_dirtyable_memory();
+	unsigned long dirtyable_memory;
+	unsigned long nr_mapped;
 	struct task_struct *tsk;
+	int is_subset = 0;
+
+#ifdef CONFIG_CPUSETS
+	if (unlikely(nodes &&
+			!nodes_subset(node_online_map, *nodes))) {
+		int node;
+
+		/*
+		 * Calculate the limits relative to the current cpuset.
+		 *
+		 * We do not disregard highmem because all nodes (except
+		 * maybe node 0) have either all memory in HIGHMEM (32 bit) or
+		 * all memory in non HIGHMEM (64 bit). If we would disregard
+		 * highmem then cpuset throttling would not work on 32 bit.
+		 */
+		is_subset = 1;
+		memset(dl, 0, sizeof(struct dirty_limits));
+		dirtyable_memory = 0;
+		nr_mapped = 0;
+		for_each_node_mask(node, *nodes) {
+			if (!node_online(node))
+				continue;
+			dl->nr_dirty += node_page_state(node, NR_FILE_DIRTY);
+			dl->nr_unstable +=
+				node_page_state(node, NR_UNSTABLE_NFS);
+			dl->nr_writeback +=
+				node_page_state(node, NR_WRITEBACK);
+			dirtyable_memory +=
+				node_page_state(node, NR_ACTIVE) +
+				node_page_state(node, NR_INACTIVE) +
+				node_page_state(node, NR_FREE_PAGES);
+			nr_mapped += node_page_state(node, NR_FILE_MAPPED) +
+				node_page_state(node, NR_ANON_PAGES);
+		}
+		dirtyable_memory -= highmem_dirtyable_memory(nodes,
+							     dirtyable_memory);
+	} else
+#endif
+	{
+		/* Global limits */
+		dl->nr_dirty = global_page_state(NR_FILE_DIRTY);
+		dl->nr_unstable = global_page_state(NR_UNSTABLE_NFS);
+		dl->nr_writeback = global_page_state(NR_WRITEBACK);
+		dirtyable_memory = determine_dirtyable_memory();
+		nr_mapped = global_page_state(NR_FILE_MAPPED) +
+			global_page_state(NR_ANON_PAGES);
+	}
 
 	unmapped_ratio = 100 - ((global_page_state(NR_FILE_MAPPED) +
 				global_page_state(NR_ANON_PAGES)) * 100) /
-					available_memory;
-
+					vm_total_pages;
 	dirty_ratio = vm_dirty_ratio;
 	if (dirty_ratio > unmapped_ratio / 2)
 		dirty_ratio = unmapped_ratio / 2;

@@ -185,15 +243,16 @@ get_dirty_limits(long *pbackground, long
 	if (background_ratio >= dirty_ratio)
 		background_ratio = dirty_ratio / 2;
 
-	background = (background_ratio * available_memory) / 100;
-	dirty = (dirty_ratio * available_memory) / 100;
+	background = (background_ratio * dirtyable_memory) / 100;
+	dirty = (dirty_ratio * dirtyable_memory) / 100;
 	tsk = current;
 	if (tsk->flags & PF_LESS_THROTTLE || rt_task(tsk)) {
 		background += background / 4;
 		dirty += dirty / 4;
 	}
-	*pbackground = background;
-	*pdirty = dirty;
+	dl->thresh_background = background;
+	dl->thresh_dirty = dirty;
+	return is_subset;
 }
 
 /*

@@ -206,8 +265,7 @@ get_dirty_limits(long *pbackground, long
 static void balance_dirty_pages(struct address_space *mapping)
 {
 	long nr_reclaimable;
-	long background_thresh;
-	long dirty_thresh;
+	struct dirty_limits dl;
 	unsigned long pages_written = 0;
 	unsigned long write_chunk = sync_writeback_pages();
 

@@ -222,11 +280,12 @@ static void balance_dirty_pages(struct a
 			.range_cyclic	= 1,
 		};
 
-		get_dirty_limits(&background_thresh, &dirty_thresh, mapping);
-		nr_reclaimable = global_page_state(NR_FILE_DIRTY) +
-					global_page_state(NR_UNSTABLE_NFS);
-		if (nr_reclaimable + global_page_state(NR_WRITEBACK) <=
-			dirty_thresh)
+		if (get_dirty_limits(&dl, mapping,
+				&cpuset_current_mems_allowed))
+			wbc.nodes = &cpuset_current_mems_allowed;
+		nr_reclaimable = dl.nr_dirty + dl.nr_unstable;
+		if (nr_reclaimable + dl.nr_writeback <=
+			dl.thresh_dirty)
 				break;
 
 		if (!dirty_exceeded)

@@ -240,13 +299,10 @@ static void balance_dirty_pages(struct a
 		 */
 		if (nr_reclaimable) {
 			writeback_inodes(&wbc);
-			get_dirty_limits(&background_thresh,
-					 	&dirty_thresh, mapping);
-			nr_reclaimable = global_page_state(NR_FILE_DIRTY) +
-					global_page_state(NR_UNSTABLE_NFS);
-			if (nr_reclaimable +
-				global_page_state(NR_WRITEBACK)
-					<= dirty_thresh)
+			get_dirty_limits(&dl, mapping,
+				&cpuset_current_mems_allowed);
+			nr_reclaimable = dl.nr_dirty + dl.nr_unstable;
+			if (nr_reclaimable + dl.nr_writeback <= dl.thresh_dirty)
 						break;
 			pages_written += write_chunk - wbc.nr_to_write;
 			if (pages_written >= write_chunk)

@@ -255,8 +311,8 @@ static void balance_dirty_pages(struct a
 		congestion_wait(WRITE, HZ/10);
 	}
 
-	if (nr_reclaimable + global_page_state(NR_WRITEBACK)
-		<= dirty_thresh && dirty_exceeded)
+	if (nr_reclaimable + dl.nr_writeback
+		<= dl.thresh_dirty && dirty_exceeded)
 			dirty_exceeded = 0;
 
 	if (writeback_in_progress(bdi))

@@ -271,8 +327,9 @@ static void balance_dirty_pages(struct a
 	 * background_thresh, to keep the amount of dirty memory low.
 	 */
 	if ((laptop_mode && pages_written) ||
-	     (!laptop_mode && (nr_reclaimable > background_thresh)))
-		pdflush_operation(background_writeout, 0, NULL);
+	     (!laptop_mode && (nr_reclaimable > dl.thresh_background)))
+		pdflush_operation(background_writeout, 0,
+			&cpuset_current_mems_allowed);
 }
 
 void set_page_dirty_balance(struct page *page)

@@ -329,8 +386,7 @@ EXPORT_SYMBOL(balance_dirty_pages_rateli
 
 void throttle_vm_writeout(gfp_t gfp_mask)
 {
-	long background_thresh;
-	long dirty_thresh;
+	struct dirty_limits dl;
 
 	if ((gfp_mask & (__GFP_FS|__GFP_IO)) != (__GFP_FS|__GFP_IO)) {
 		/*

@@ -342,27 +398,26 @@ void throttle_vm_writeout(gfp_t gfp_mask
 		return;
 	}
 
-        for ( ; ; ) {
-		get_dirty_limits(&background_thresh, &dirty_thresh, NULL);
+	for ( ; ; ) {
+		get_dirty_limits(&dl, NULL, &node_online_map);
 
-                /*
-                 * Boost the allowable dirty threshold a bit for page
-                 * allocators so they don't get DoS'ed by heavy writers
-                 */
-                dirty_thresh += dirty_thresh / 10;      /* wheeee... */
-
-                if (global_page_state(NR_UNSTABLE_NFS) +
-			global_page_state(NR_WRITEBACK) <= dirty_thresh)
-                        	break;
-                congestion_wait(WRITE, HZ/10);
-        }
+		/*
+		 * Boost the allowable dirty threshold a bit for page
+		 * allocators so they don't get DoS'ed by heavy writers
+		 */
+		dl.thresh_dirty += dl.thresh_dirty / 10; /* wheeee... */
+
+		if (dl.nr_unstable + dl.nr_writeback <= dl.thresh_dirty)
+			break;
+		congestion_wait(WRITE, HZ/10);
+	}
 }
 
 /*
  * writeback at least _min_pages, and keep writing until the amount of dirty
  * memory is less than the background threshold, or until we're all clean.
  */
-static void background_writeout(unsigned long _min_pages, nodemask_t *unused)
+static void background_writeout(unsigned long _min_pages, nodemask_t *nodes)
 {
 	long min_pages = _min_pages;
 	struct writeback_control wbc = {

@@ -375,12 +430,11 @@ static void background_writeout(unsigned
 	};
 
 	for ( ; ; ) {
-		long background_thresh;
-		long dirty_thresh;
+		struct dirty_limits dl;
 
-		get_dirty_limits(&background_thresh, &dirty_thresh, NULL);
-		if (global_page_state(NR_FILE_DIRTY) +
-			global_page_state(NR_UNSTABLE_NFS) < background_thresh
+		if (get_dirty_limits(&dl, NULL, nodes))
+			wbc.nodes = nodes;
+		if (dl.nr_dirty + dl.nr_unstable < dl.thresh_background
 				&& min_pages <= 0)
 			break;
 		wbc.encountered_congestion = 0;

diff -uprN -X 0/Documentation/dontdiff 3/mm/vmscan.c 4/mm/vmscan.c
@@ -1198,7 +1198,8 @@ unsigned long try_to_free_pages(struct z
 		 */
 		if (total_scanned > sc.swap_cluster_max +
 					sc.swap_cluster_max / 2) {
-			wakeup_pdflush(laptop_mode ? 0 : total_scanned, NULL);
+			wakeup_pdflush(laptop_mode ? 0 : total_scanned,
+				&cpuset_current_mems_allowed);
 			sc.may_writepage = 1;
 		}
 

@@ -89,7 +89,7 @@ static inline void wait_on_inode(struct
 int wakeup_pdflush(long nr_pages, nodemask_t *nodes);
 void laptop_io_completion(void);
 void laptop_sync_completion(void);
-void throttle_vm_writeout(gfp_t gfp_mask);
+void throttle_vm_writeout(nodemask_t *nodes,gfp_t gfp_mask);
 
 /* These are exported to sysctl. */
 extern int dirty_background_ratio;

@@ -384,7 +384,7 @@ void balance_dirty_pages_ratelimited_nr(
 }
 EXPORT_SYMBOL(balance_dirty_pages_ratelimited_nr);
 
-void throttle_vm_writeout(gfp_t gfp_mask)
+void throttle_vm_writeout(nodemask_t *nodes, gfp_t gfp_mask)
 {
 	struct dirty_limits dl;
 

@@ -399,7 +399,7 @@ void throttle_vm_writeout(gfp_t gfp_mask
 	}
 
 	for ( ; ; ) {
-		get_dirty_limits(&dl, NULL, &node_online_map);
+		get_dirty_limits(&dl, NULL, nodes);
 
 		/*
 		 * Boost the allowable dirty threshold a bit for page

diff -uprN -X 0/Documentation/dontdiff 4/mm/vmscan.c 5/mm/vmscan.c
@@ -1079,7 +1079,7 @@ static unsigned long shrink_zone(int pri
 		}
 	}
 
-	throttle_vm_writeout(sc->gfp_mask);
+	throttle_vm_writeout(&cpuset_current_mems_allowed, sc->gfp_mask);
 
 	atomic_dec(&zone->reclaim_in_progress);
 	return nr_reclaimed;

diff -uprN -X 0/Documentation/dontdiff 4/include/linux/writeback.h 5/include/linux/writeback.h
@@ -89,7 +89,7 @@ static inline void wait_on_inode(struct 
 int wakeup_pdflush(long nr_pages, nodemask_t *nodes);
 void laptop_io_completion(void);
 void laptop_sync_completion(void);
-void throttle_vm_writeout(gfp_t gfp_mask);
+void throttle_vm_writeout(nodemask_t *nodes,gfp_t gfp_mask);
 
 /* These are exported to sysctl. */
 extern int dirty_background_ratio;

diff -uprN -X 0/Documentation/dontdiff 4/mm/page-writeback.c 5/mm/page-writeback.c
@@ -384,7 +384,7 @@ void balance_dirty_pages_ratelimited_nr(
 }
 EXPORT_SYMBOL(balance_dirty_pages_ratelimited_nr);
 
-void throttle_vm_writeout(gfp_t gfp_mask)
+void throttle_vm_writeout(nodemask_t *nodes, gfp_t gfp_mask)
 {
 	struct dirty_limits dl;
 

@@ -399,7 +399,7 @@ void throttle_vm_writeout(gfp_t gfp_mask
 	}
 
 	for ( ; ; ) {
-		get_dirty_limits(&dl, NULL, &node_online_map);
+		get_dirty_limits(&dl, NULL, nodes);
 
 		/*
 		 * Boost the allowable dirty threshold a bit for page

diff -uprN -X 0/Documentation/dontdiff 4/mm/vmscan.c 5/mm/vmscan.c
@@ -1079,7 +1079,7 @@ static unsigned long shrink_zone(int pri
 		}
 	}
 
-	throttle_vm_writeout(sc->gfp_mask);
+	throttle_vm_writeout(&cpuset_current_mems_allowed, sc->gfp_mask);
 
 	atomic_dec(&zone->reclaim_in_progress);
 	return nr_reclaimed;

diff -uprN -X 0/Documentation/dontdiff 5/mm/page-writeback.c 6/mm/page-writeback.c
@@ -177,7 +177,6 @@ get_dirty_limits(struct dirty_limits *dl
 	int unmapped_ratio;
 	long background;
 	long dirty;
-	unsigned long available_memory = determine_dirtyable_memory();
 	unsigned long dirtyable_memory;
 	unsigned long nr_mapped;
 	struct task_struct *tsk;

diff -uprN -X 0/Documentation/dontdiff 6/include/linux/cpuset.h 7/include/linux/cpuset.h
@@ -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
  */

142 lines not on this page · raw message

diff -uprN -X 0/Documentation/dontdiff 6/mm/page-writeback.c 7/mm/page-writeback.c
@@ -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;