linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Peter Zijlstra <a.p.zijlstra@chello.nl>
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,
	trond.myklebust@fys.uio.no, yingchao.zhou@gmail.com,
	andrea@suse.de
Subject: [PATCH 15/17] lib: floating proportions _single
Date: Thu, 14 Jun 2007 23:58:32 +0200	[thread overview]
Message-ID: <20070614220447.296464031@chello.nl> (raw)
In-Reply-To: 20070614215817.389524447@chello.nl

[-- Attachment #1: proportions_single.patch --]
[-- Type: text/plain, Size: 9457 bytes --]

Provide a prop_local that does not use a percpu variable for its counter.
This is useful for items that are not (or infrequently) accessed from
multiple context and/or are plenty enought that the percpu_counter overhead
will hurt (tasks).

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
---
 include/linux/proportions.h |  112 +++++++++++++++++++++++++++++++++++++--
 lib/proportions.c           |  124 ++++++++++++++++++++++++++++++++++++++++----
 2 files changed, 218 insertions(+), 18 deletions(-)

Index: linux-2.6/include/linux/proportions.h
===================================================================
--- linux-2.6.orig/include/linux/proportions.h
+++ linux-2.6/include/linux/proportions.h
@@ -45,7 +45,11 @@ void prop_change_shift(struct prop_descr
 struct prop_global *prop_get_global(struct prop_descriptor *pd);
 void prop_put_global(struct prop_descriptor *pd, struct prop_global *pg);
 
-struct prop_local {
+/*
+ * ----- PERCPU ------
+ */
+
+struct prop_local_percpu {
 	/*
 	 * the local events counter
 	 */
@@ -59,23 +63,117 @@ struct prop_local {
 	spinlock_t lock;		/* protect the snapshot state */
 };
 
-void prop_local_init(struct prop_local *pl);
-void prop_local_destroy(struct prop_local *pl);
+void prop_local_init_percpu(struct prop_local_percpu *pl);
+void prop_local_destroy_percpu(struct prop_local_percpu *pl);
 
-void prop_norm(struct prop_global *pg, struct prop_local *pl);
+void prop_norm_percpu(struct prop_global *pg, struct prop_local_percpu *pl);
 
 /*
  *   ++x_{j}, ++t
  */
 static inline
-void __prop_inc(struct prop_global *pg, struct prop_local *pl)
+void __prop_inc_percpu(struct prop_global *pg, struct prop_local_percpu *pl)
 {
-	prop_norm(pg, pl);
+	prop_norm_percpu(pg, pl);
 	percpu_counter_mod(&pl->events, 1);
 	percpu_counter_mod(&pg->events, 1);
 }
 
-void prop_fraction(struct prop_global *pg, struct prop_local *pl,
+void prop_fraction_percpu(struct prop_global *pg, struct prop_local_percpu *pl,
+		long *numerator, long *denominator);
+
+/*
+ * ----- SINGLE ------
+ */
+
+struct prop_local_single {
+	/*
+	 * the local events counter
+	 */
+	unsigned long events;
+
+	/*
+	 * snapshot of the last seen global state
+	 * and a lock protecting this state
+	 */
+	int shift;
+	unsigned long period;
+	spinlock_t lock;		/* protect the snapshot state */
+};
+
+void prop_local_init_single(struct prop_local_single *pl);
+void prop_local_destroy_single(struct prop_local_single *pl);
+
+void prop_norm_single(struct prop_global *pg, struct prop_local_single *pl);
+
+/*
+ *   ++x_{j}, ++t
+ */
+static inline
+void __prop_inc_single(struct prop_global *pg, struct prop_local_single *pl)
+{
+	prop_norm_single(pg, pl);
+	pl->events++;
+	percpu_counter_mod(&pg->events, 1);
+}
+
+void prop_fraction_single(struct prop_global *pg, struct prop_local_single *pl,
 		long *numerator, long *denominator);
 
+/*
+ * ----- GLUE ------
+ */
+
+#undef TYPE_EQUAL
+#define TYPE_EQUAL(expr, type) \
+	__builtin_types_compatible_p(typeof(expr), type)
+
+extern int __bad_prop_local(void);
+
+#define prop_local_init(prop_local)					\
+do {									\
+	if (TYPE_EQUAL(*(prop_local), struct prop_local_percpu))	\
+		prop_local_init_percpu(					\
+			(struct prop_local_percpu *)(prop_local));	\
+	else if (TYPE_EQUAL(*(prop_local), struct prop_local_single))	\
+		prop_local_init_single(					\
+			(struct prop_local_single *)(prop_local));	\
+	else __bad_prop_local();					\
+} while (0)
+
+#define prop_local_destroy(prop_local)					\
+do {									\
+	if (TYPE_EQUAL(*(prop_local), struct prop_local_percpu))	\
+		prop_local_destroy_percpu(				\
+			(struct prop_local_percpu *)(prop_local));	\
+	else if (TYPE_EQUAL(*(prop_local), struct prop_local_single))	\
+		prop_local_destroy_single(				\
+			(struct prop_local_single *)(prop_local));	\
+	else __bad_prop_local();					\
+} while (0)
+
+#define __prop_inc(prop_global, prop_local)				\
+do {									\
+	if (TYPE_EQUAL(*(prop_local), struct prop_local_percpu))	\
+		__prop_inc_percpu(prop_global,				\
+			(struct prop_local_percpu *)(prop_local)); 	\
+	else if (TYPE_EQUAL(*(prop_local), struct prop_local_single))	\
+		__prop_inc_single(prop_global,				\
+			(struct prop_local_single *)(prop_local)); 	\
+	else __bad_prop_local();					\
+} while (0)
+
+#define prop_fraction(prop_global, prop_local, num, denom)		\
+do {									\
+	if (TYPE_EQUAL(*(prop_local), struct prop_local_percpu))	\
+		prop_fraction_percpu(prop_global,			\
+			(struct prop_local_percpu *)(prop_local),	\
+			num, denom);					\
+	else if (TYPE_EQUAL(*(prop_local), struct prop_local_single))	\
+		prop_fraction_single(prop_global,			\
+			(struct prop_local_single *)(prop_local),	\
+			num, denom);					\
+	else __bad_prop_local();					\
+} while (0)
+
 #endif /* _LINUX_PROPORTIONS_H */
Index: linux-2.6/lib/proportions.c
===================================================================
--- linux-2.6.orig/lib/proportions.c
+++ linux-2.6/lib/proportions.c
@@ -149,22 +149,31 @@ void prop_put_global(struct prop_descrip
 	rcu_read_unlock();
 }
 
-static void prop_adjust_shift(struct prop_local *pl, int new_shift)
+static void
+__prop_adjust_shift(int *pl_shift, unsigned long *pl_period, int new_shift)
 {
-	int offset = pl->shift - new_shift;
+	int offset = *pl_shift - new_shift;
 
 	if (!offset)
 		return;
 
 	if (offset < 0)
-		pl->period <<= -offset;
+		*pl_period <<= -offset;
 	else
-		pl->period >>= offset;
+		*pl_period >>= offset;
 
-	pl->shift = new_shift;
+	*pl_shift = new_shift;
 }
 
-void prop_local_init(struct prop_local *pl)
+#define prop_adjust_shift(prop_local, pg_shift)			\
+	__prop_adjust_shift(&(prop_local)->shift,		\
+			    &(prop_local)->period, pg_shift)
+
+/*
+ * PERCPU
+ */
+
+void prop_local_init_percpu(struct prop_local_percpu *pl)
 {
 	spin_lock_init(&pl->lock);
 	pl->shift = 0;
@@ -172,7 +181,7 @@ void prop_local_init(struct prop_local *
 	percpu_counter_init_irq(&pl->events, 0);
 }
 
-void prop_local_destroy(struct prop_local *pl)
+void prop_local_destroy_percpu(struct prop_local_percpu *pl)
 {
 	percpu_counter_destroy(&pl->events);
 }
@@ -184,8 +193,7 @@ void prop_local_destroy(struct prop_loca
  *     x_{j} -= x_{j}/2;
  *     c_{j}++;
  */
-void prop_norm(struct prop_global *pg,
-		struct prop_local *pl)
+void prop_norm_percpu(struct prop_global *pg, struct prop_local_percpu *pl)
 {
 	unsigned long period = 1UL << (pg->shift - 1);
 	unsigned long period_mask = ~(period - 1);
@@ -242,17 +250,111 @@ void prop_norm(struct prop_global *pg,
  *
  *   p_{j} = x_{j} / (period/2 + t % period/2)
  */
-void prop_fraction(struct prop_global *pg, struct prop_local *pl,
+void prop_fraction_percpu(struct prop_global *pg, struct prop_local_percpu *pl,
 		long *numerator, long *denominator)
 {
 	unsigned long period_2 = 1UL << (pg->shift - 1);
 	unsigned long counter_mask = period_2 - 1;
 	unsigned long global_count;
 
-	prop_norm(pg, pl);
+	prop_norm_percpu(pg, pl);
 	*numerator = percpu_counter_read_positive(&pl->events);
 
 	global_count = percpu_counter_read(&pg->events);
 	*denominator = period_2 + (global_count & counter_mask);
 }
 
+/*
+ * SINGLE
+ */
+
+void prop_local_init_single(struct prop_local_single *pl)
+{
+	spin_lock_init(&pl->lock);
+	pl->shift = 0;
+	pl->period = 0;
+	pl->events = 0;
+}
+
+void prop_local_destroy_single(struct prop_local_single *pl)
+{
+}
+
+/*
+ * Catch up with missed period expirations.
+ *
+ *   until (c_{j} == c)
+ *     x_{j} -= x_{j}/2;
+ *     c_{j}++;
+ */
+void prop_norm_single(struct prop_global *pg, struct prop_local_single *pl)
+{
+	unsigned long period = 1UL << (pg->shift - 1);
+	unsigned long period_mask = ~(period - 1);
+	unsigned long global_period;
+	unsigned long flags;
+
+	global_period = percpu_counter_read(&pg->events);
+	global_period &= period_mask;
+
+	/*
+	 * Fast path - check if the local and global period count still match
+	 * outside of the lock.
+	 */
+	if (pl->period == global_period)
+		return;
+
+	spin_lock_irqsave(&pl->lock, flags);
+	prop_adjust_shift(pl, pg->shift);
+	/*
+	 * For each missed period, we half the local counter.
+	 * basically:
+	 *   pl->events >> (global_period - pl->period);
+	 *
+	 * but since the distributed nature of single counters make division
+	 * rather hard, use a regular subtraction loop. This is safe, because
+	 * the events will only every be incremented, hence the subtraction
+	 * can never result in a negative number.
+	 */
+	while (pl->period != global_period) {
+		unsigned long val = pl->events;
+		unsigned long half = (val + 1) >> 1;
+
+		/*
+		 * Half of zero won't be much less, break out.
+		 * This limits the loop to shift iterations, even
+		 * if we missed a million.
+		 */
+		if (!val)
+			break;
+
+		/*
+		 * Iff shift >32 half might exceed the limits of
+		 * the regular single_counter_mod.
+		 */
+		pl->events -= half;
+		pl->period += period;
+	}
+	pl->period = global_period;
+	spin_unlock_irqrestore(&pl->lock, flags);
+}
+
+/*
+ * Obtain an fraction of this proportion
+ *
+ *   p_{j} = x_{j} / (period/2 + t % period/2)
+ */
+void prop_fraction_single(struct prop_global *pg, struct prop_local_single *pl,
+		long *numerator, long *denominator)
+{
+	unsigned long period_2 = 1UL << (pg->shift - 1);
+	unsigned long counter_mask = period_2 - 1;
+	unsigned long global_count;
+
+	prop_norm_single(pg, pl);
+	*numerator = pl->events;
+
+	global_count = percpu_counter_read(&pg->events);
+	*denominator = period_2 + (global_count & counter_mask);
+}
+

-- 


  parent reply	other threads:[~2007-06-14 22:13 UTC|newest]

Thread overview: 23+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2007-06-14 21:58 [PATCH 00/17] per device dirty throttling -v7 Peter Zijlstra
2007-06-14 21:58 ` [PATCH 01/17] nfs: remove congestion_end() Peter Zijlstra
2007-06-14 21:58 ` [PATCH 02/17] lib: percpu_counter variable batch Peter Zijlstra
2007-06-14 21:58 ` [PATCH 03/17] lib: percpu_counter_mod64 Peter Zijlstra
2007-06-14 21:58 ` [PATCH 04/17] lib: percpu_counter_set Peter Zijlstra
2007-06-14 21:58 ` [PATCH 05/17] lib: percpu_count_sum_signed() Peter Zijlstra
2007-07-17 16:32   ` Josef Sipek
2007-07-17 16:35     ` Josef Sipek
2007-06-14 21:58 ` [PATCH 06/17] lib: percpu_counter_init_irq Peter Zijlstra
2007-07-17 16:35   ` Josef Sipek
2007-06-14 21:58 ` [PATCH 07/17] mm: bdi init hooks Peter Zijlstra
2007-06-14 21:58 ` [PATCH 08/17] containers: " Peter Zijlstra
2007-06-14 21:58 ` [PATCH 09/17] mtd: give mtdconcat devices their own backing_dev_info Peter Zijlstra
2007-06-14 21:58 ` [PATCH 10/17] mm: scalable bdi statistics counters Peter Zijlstra
2007-06-14 21:58 ` [PATCH 11/17] mm: count reclaimable pages per BDI Peter Zijlstra
2007-06-14 21:58 ` [PATCH 12/17] mm: count writeback " Peter Zijlstra
2007-06-14 21:58 ` [PATCH 13/17] mm: expose BDI statistics in sysfs Peter Zijlstra
2007-06-14 21:58 ` [PATCH 14/17] lib: floating proportions Peter Zijlstra
2007-06-14 21:58 ` Peter Zijlstra [this message]
2007-06-14 21:58 ` [PATCH 16/17] mm: per device dirty threshold Peter Zijlstra
2007-06-14 21:58 ` [PATCH 17/17] mm: dirty balancing for tasks Peter Zijlstra
2007-06-14 23:14 ` [PATCH 00/17] per device dirty throttling -v7 Andrew Morton
2007-07-17 10:10 ` Miklos Szeredi

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=20070614220447.296464031@chello.nl \
    --to=a.p.zijlstra@chello.nl \
    --cc=akpm@linux-foundation.org \
    --cc=andrea@suse.de \
    --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 \
    --cc=trond.myklebust@fys.uio.no \
    --cc=yingchao.zhou@gmail.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).