[RFC PATCH v23 09/10] mm: add the rss_stat_batch boot parameter

[Mathieu Desnoyers]

The RSS counters use a batch size of 32: each CPU accumulates up to 31
pages in either direction before propagating a carry into the counter
tree.  A smaller batch improves the accuracy of the approximate RSS, and
a larger batch reduces the cost of updates.

Add the rss_stat_batch= boot parameter to compare batch sizes on a
given machine, along with the percpu_counter_tree.arity= boot parameter
for the tree shape.  It accepts a power of 2 between 2 and 128, and is
ignored with a warning otherwise.

Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@xxxxxxxxxxxx>
---
 .../admin-guide/kernel-parameters.txt         | 10 ++++++++
 kernel/fork.c                                 | 23 ++++++++++++++++---
 2 files changed, 30 insertions(+), 3 deletions(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index c368affa2115..ba2bdeb1480b 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -6792,6 +6792,16 @@ Kernel parameters
 			debug mode. Defaults to CONFIG_RSEQ_DEBUG_DEFAULT_ENABLE.
 			Format: <bool>
 
+	rss_stat_batch=	[KNL,SMP]
+			Format: <integer>
+			Batch size of the per-mm RSS counters: the number of
+			pages a CPU accumulates before propagating them into
+			the counter tree. A power of 2 between 2 and 128.
+			A smaller batch improves the accuracy of the
+			approximate RSS, a larger batch reduces the update
+			cost. Default: 32.
+			This parameter is meant for performance comparison.
+
 	rt_group_sched=	[KNL] Enable or disable SCHED_RR/FIFO group scheduling
 			when CONFIG_RT_GROUP_SCHED=y. Defaults to
 			!CONFIG_RT_GROUP_SCHED_DEFAULT_DISABLED.
diff --git a/kernel/fork.c b/kernel/fork.c
index ac4eb1370e62..d0641700cd9c 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -138,9 +138,26 @@
 #define MAX_THREADS FUTEX_TID_MASK
 
 /*
- * Batch size of rss stat approximation
+ * Batch size of rss stat approximation, tunable with the rss_stat_batch=
+ * boot parameter to compare batch sizes on a given machine.
  */
-#define RSS_STAT_BATCH_SIZE	32
+static unsigned int rss_stat_batch_size __ro_after_init = 32;
+
+static int __init setup_rss_stat_batch(char *str)
+{
+	unsigned int batch;
+
+	if (kstrtouint(str, 0, &batch) || batch < 2 || !is_power_of_2(batch) ||
+	    batch > PERCPU_COUNTER_TREE_MAX_BATCH) {
+		pr_warn("rss_stat_batch: expecting a power of 2 between 2 and %u\n",
+			PERCPU_COUNTER_TREE_MAX_BATCH);
+		return 1;
+	}
+	rss_stat_batch_size = batch;
+	pr_info("rss_stat_batch: %u\n", batch);
+	return 1;
+}
+__setup("rss_stat_batch=", setup_rss_stat_batch);
 
 /*
  * Protected counters by write_lock_irq(&tasklist_lock)
@@ -1149,7 +1166,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p)
 	if (mm_alloc_sched(mm))
 		goto fail_sched;
 
-	if (percpu_counter_tree_init_many_lazy(mm->rss_stat, NR_MM_COUNTERS, RSS_STAT_BATCH_SIZE))
+	if (percpu_counter_tree_init_many_lazy(mm->rss_stat, NR_MM_COUNTERS, rss_stat_batch_size))
 		goto fail_pcpu;
 
 	lru_gen_init_mm(mm);
-- 
2.47.3