diff mbox series

[v4,1/2] ksm: count allocated ksm rmap_items for each process

Message ID 20220824124615.223158-1-xu.xin16@zte.com.cn (mailing list archive)
State New
Headers show
Series ksm: count allocated rmap_items and update documentation | expand

Commit Message

CGEL Aug. 24, 2022, 12:46 p.m. UTC 
KSM can save memory by merging identical pages, but also can consume
additional memory, because it needs to generate rmap_items to save
each scanned page's brief rmap information. Some of these pages may
be merged, but some may not be abled to be merged after being checked
several times, which are unprofitable memory consumed.

The information about whether KSM save memory or consume memory in
system-wide range can be determined by the comprehensive calculation
of pages_sharing, pages_shared, pages_unshared and pages_volatile.
A simple approximate calculation:

	profit =~ pages_sharing * sizeof(page) - (all_rmap_items) *
	         sizeof(rmap_item);

where all_rmap_items equals to the sum of pages_sharing, pages_shared,
pages_unshared and pages_volatile.

But we cannot calculate this kind of ksm profit inner single-process wide
because the information of ksm rmap_item's number of a process is lacked.
For user applications, if this kind of information could be obtained,
it helps upper users know how beneficial the ksm-policy (like madvise)
they are using brings, and then optimize their app code. For example,
one application madvise 1000 pages as MERGEABLE, while only a few pages
are really merged, then it's not cost-efficient.

So we add a new interface /proc/<pid>/ksm_rmp_items for each process to
indicate the total allocated ksm rmap_items of this process. Similarly,
we can calculate the ksm profit approximately for a single-process by:

	profit =~ ksm_merging_pages * sizeof(page) - ksm_rmp_items *
		 sizeof(rmap_item);

where ksm_merging_pages and ksm_rmp_items are both under /proc/<pid>/.

Signed-off-by: xu xin <xu.xin16@zte.com.cn>
Reviewed-by: Xiaokai Ran <ran.xiaokai@zte.com.cn>
Reviewed-by: Yang Yang <yang.yang29@zte.com.cn>
Signed-off-by: CGEL ZTE <cgel.zte@gmail.com>
---
 fs/proc/base.c           | 15 +++++++++++++++
 include/linux/mm_types.h |  5 +++++
 mm/ksm.c                 |  2 ++
 3 files changed, 22 insertions(+)


base-commit: 68a00424bf69036970ced7930f9e4d709b4a6423

Comments

Matthew Wilcox Aug. 24, 2022, 12:58 p.m. UTC | #1 
On Wed, Aug 24, 2022 at 12:46:15PM +0000, xu xin wrote:
>  #ifdef CONFIG_KSM
>  	ONE("ksm_merging_pages",  S_IRUSR, proc_pid_ksm_merging_pages),
> +	ONE("ksm_rmp_items",  S_IRUSR, proc_pid_ksm_rmp_items),

You misspelled "rmap" in the file name.

> +		/*
> +		 * Represent how many pages are checked for ksm merging
> +		 * including merged and not merged.
> +		 */
> +		unsigned long ksm_rmp_items;

Also here.
Alexey Dobriyan Aug. 28, 2022, 6:42 p.m. UTC | #2 
On Wed, Aug 24, 2022 at 12:46:15PM +0000, xu xin wrote:
> +static int proc_pid_ksm_rmp_items(struct seq_file *m, struct pid_namespace *ns,
> +				struct pid *pid, struct task_struct *task)
> +{
> +	struct mm_struct *mm;
> +
> +	mm = get_task_mm(task);
> +	if (mm) {
> +		seq_printf(m, "%lu\n", mm->ksm_rmp_items);
> +		mmput(mm);
> +	}
> +
> +	return 0;
> +}
>  #endif /* CONFIG_KSM */
>  
>  #ifdef CONFIG_STACKLEAK_METRICS
> @@ -3334,6 +3347,7 @@ static const struct pid_entry tgid_base_stuff[] = {
>  #endif
>  #ifdef CONFIG_KSM
>  	ONE("ksm_merging_pages",  S_IRUSR, proc_pid_ksm_merging_pages),
> +	ONE("ksm_rmp_items",  S_IRUSR, proc_pid_ksm_rmp_items),
>  #endif

Another tiny /proc/$pid/ file?

Guys, this problem with "find /proc" instantiating megabytes is not
getting better only worse.

How did KSM didn't get its own /proc/*/ksm file with many values?

Maybe add /proc/*/ksm and start filling it with stuff leaving
/proc/*/ksm_merging_pages alone?
diff mbox series

Patch

diff --git a/fs/proc/base.c b/fs/proc/base.c
index 4ead8cf654e4..9977e17885c2 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -3199,6 +3199,19 @@  static int proc_pid_ksm_merging_pages(struct seq_file *m, struct pid_namespace *
 
 	return 0;
 }
+static int proc_pid_ksm_rmp_items(struct seq_file *m, struct pid_namespace *ns,
+				struct pid *pid, struct task_struct *task)
+{
+	struct mm_struct *mm;
+
+	mm = get_task_mm(task);
+	if (mm) {
+		seq_printf(m, "%lu\n", mm->ksm_rmp_items);
+		mmput(mm);
+	}
+
+	return 0;
+}
 #endif /* CONFIG_KSM */
 
 #ifdef CONFIG_STACKLEAK_METRICS
@@ -3334,6 +3347,7 @@  static const struct pid_entry tgid_base_stuff[] = {
 #endif
 #ifdef CONFIG_KSM
 	ONE("ksm_merging_pages",  S_IRUSR, proc_pid_ksm_merging_pages),
+	ONE("ksm_rmp_items",  S_IRUSR, proc_pid_ksm_rmp_items),
 #endif
 };
 
@@ -3671,6 +3685,7 @@  static const struct pid_entry tid_base_stuff[] = {
 #endif
 #ifdef CONFIG_KSM
 	ONE("ksm_merging_pages",  S_IRUSR, proc_pid_ksm_merging_pages),
+	ONE("ksm_rmp_items",  S_IRUSR, proc_pid_ksm_rmp_items),
 #endif
 };
 
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index d6ec33438dc1..a2a8da1ccb31 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -656,6 +656,11 @@  struct mm_struct {
 		 * merging.
 		 */
 		unsigned long ksm_merging_pages;
+		/*
+		 * Represent how many pages are checked for ksm merging
+		 * including merged and not merged.
+		 */
+		unsigned long ksm_rmp_items;
 #endif
 #ifdef CONFIG_LRU_GEN
 		struct {
diff --git a/mm/ksm.c b/mm/ksm.c
index a98bc3beb874..66d686039010 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -387,6 +387,7 @@  static inline struct rmap_item *alloc_rmap_item(void)
 static inline void free_rmap_item(struct rmap_item *rmap_item)
 {
 	ksm_rmap_items--;
+	rmap_item->mm->ksm_rmp_items--;
 	rmap_item->mm = NULL;	/* debug safety */
 	kmem_cache_free(rmap_item_cache, rmap_item);
 }
@@ -2231,6 +2232,7 @@  static struct rmap_item *get_next_rmap_item(struct mm_slot *mm_slot,
 	if (rmap_item) {
 		/* It has already been zeroed */
 		rmap_item->mm = mm_slot->mm;
+		rmap_item->mm->ksm_rmp_items++;
 		rmap_item->address = addr;
 		rmap_item->rmap_list = *rmap_list;
 		*rmap_list = rmap_item;