mm: dirty balancing for tasks

Based on ideas of Andrew:
  http://marc.info/?l=linux-kernel&m=102912915020543&w=2

Scale the bdi dirty limit inversly with the tasks dirty rate.
This makes heavy writers have a lower dirty limit than the occasional writer.

Andrea proposed something similar:
  http://lwn.net/Articles/152277/

The main disadvantage to his patch is that he uses an unrelated quantity to
measure time, which leaves him with a workload dependant tunable. Other than
that the two approaches appear quite similar.

[[email protected]: fix warning]
Signed-off-by: Peter Zijlstra <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

include/linux/init_task.h

@@ -171,6 +171,7 @@ extern struct group_info init_groups;
 		[PIDTYPE_PGID] = INIT_PID_LINK(PIDTYPE_PGID),		\
 		[PIDTYPE_SID]  = INIT_PID_LINK(PIDTYPE_SID),		\
 	},								\
+	.dirties = INIT_PROP_LOCAL_SINGLE(dirties),			\
 	INIT_TRACE_IRQFLAGS						\
 	INIT_LOCKDEP							\
 }

include/linux/sched.h

@@ -74,6 +74,7 @@ struct sched_param {
 #include <linux/pid.h>
 #include <linux/percpu.h>
 #include <linux/topology.h>
+#include <linux/proportions.h>
 #include <linux/seccomp.h>
 #include <linux/rcupdate.h>
 #include <linux/futex.h>
@@ -1149,6 +1150,7 @@ struct task_struct {
 #ifdef CONFIG_FAULT_INJECTION
 	int make_it_fail;
 #endif
+	struct prop_local_single dirties;
 };
 
 /*

kernel/fork.c

@@ -107,6 +107,7 @@ static struct kmem_cache *mm_cachep;
 
 void free_task(struct task_struct *tsk)
 {
+	prop_local_destroy_single(&tsk->dirties);
 	free_thread_info(tsk->stack);
 	rt_mutex_debug_task_free(tsk);
 	free_task_struct(tsk);
@@ -163,6 +164,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
 {
 	struct task_struct *tsk;
 	struct thread_info *ti;
+	int err;
 
 	prepare_to_copy(orig);
 
@@ -178,6 +180,14 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
 
 	*tsk = *orig;
 	tsk->stack = ti;
+
+	err = prop_local_init_single(&tsk->dirties);
+	if (err) {
+		free_thread_info(ti);
+		free_task_struct(tsk);
+		return NULL;
+	}
+
 	setup_thread_stack(tsk, orig);
 
 #ifdef CONFIG_CC_STACKPROTECTOR

mm/page-writeback.c

@@ -118,6 +118,7 @@ static void background_writeout(unsigned long _min_pages);
  *
  */
 static struct prop_descriptor vm_completions;
+static struct prop_descriptor vm_dirties;
 
 static unsigned long determine_dirtyable_memory(void);
 
@@ -146,6 +147,7 @@ int dirty_ratio_handler(struct ctl_table *table, int write,
 	if (ret == 0 && write && vm_dirty_ratio != old_ratio) {
 		int shift = calc_period_shift();
 		prop_change_shift(&vm_completions, shift);
+		prop_change_shift(&vm_dirties, shift);
 	}
 	return ret;
 }
@@ -159,6 +161,11 @@ static inline void __bdi_writeout_inc(struct backing_dev_info *bdi)
 	__prop_inc_percpu(&vm_completions, &bdi->completions);
 }
 
+static inline void task_dirty_inc(struct task_struct *tsk)
+{
+	prop_inc_single(&vm_dirties, &tsk->dirties);
+}
+
 /*
  * Obtain an accurate fraction of the BDI's portion.
  */
@@ -198,6 +205,37 @@ clip_bdi_dirty_limit(struct backing_dev_info *bdi, long dirty, long *pbdi_dirty)
 	*pbdi_dirty = min(*pbdi_dirty, avail_dirty);
 }
 
+static inline void task_dirties_fraction(struct task_struct *tsk,
+		long *numerator, long *denominator)
+{
+	prop_fraction_single(&vm_dirties, &tsk->dirties,
+				numerator, denominator);
+}
+
+/*
+ * scale the dirty limit
+ *
+ * task specific dirty limit:
+ *
+ *   dirty -= (dirty/8) * p_{t}
+ */
+void task_dirty_limit(struct task_struct *tsk, long *pdirty)
+{
+	long numerator, denominator;
+	long dirty = *pdirty;
+	u64 inv = dirty >> 3;
+
+	task_dirties_fraction(tsk, &numerator, &denominator);
+	inv *= numerator;
+	do_div(inv, denominator);
+
+	dirty -= inv;
+	if (dirty < *pdirty/2)
+		dirty = *pdirty/2;
+
+	*pdirty = dirty;
+}
+
 /*
  * Work out the current dirty-memory clamping and background writeout
  * thresholds.
@@ -304,6 +342,7 @@ get_dirty_limits(long *pbackground, long *pdirty, long *pbdi_dirty,
 
 		*pbdi_dirty = bdi_dirty;
 		clip_bdi_dirty_limit(bdi, dirty, pbdi_dirty);
+		task_dirty_limit(current, pbdi_dirty);
 	}
 }
 
@@ -720,6 +759,7 @@ void __init page_writeback_init(void)
 
 	shift = calc_period_shift();
 	prop_descriptor_init(&vm_completions, shift);
+	prop_descriptor_init(&vm_dirties, shift);
 }
 
 /**
@@ -998,7 +1038,7 @@ EXPORT_SYMBOL(redirty_page_for_writepage);
  * If the mapping doesn't provide a set_page_dirty a_op, then
  * just fall through and assume that it wants buffer_heads.
  */
-int fastcall set_page_dirty(struct page *page)
+static int __set_page_dirty(struct page *page)
 {
 	struct address_space *mapping = page_mapping(page);
 
@@ -1016,6 +1056,14 @@ int fastcall set_page_dirty(struct page *page)
 	}
 	return 0;
 }
+
+int fastcall set_page_dirty(struct page *page)
+{
+	int ret = __set_page_dirty(page);
+	if (ret)
+		task_dirty_inc(current);
+	return ret;
+}
 EXPORT_SYMBOL(set_page_dirty);
 
 /*