This adds the general_profit KSM sysfs knob and the process profit metric
and process merge type knobs to ksm_stat.
1) expose general_profit metric
The documentation mentions a general profit metric, however this
metric is not calculated. In addition the formula depends on the size
of internal structures, which makes it more difficult for an
administrator to make the calculation. Adding the metric for a better
user experience.
2) document general_profit sysfs knob
3) calculate ksm process profit metric
The ksm documentation mentions the process profit metric and how to
calculate it. This adds the calculation of the metric.
4) add ksm_merge_type() function
This adds the ksm_merge_type function. The function returns the
merge type for the process. For madvise it returns "madvise", for
prctl it returns "process" and otherwise it returns "none".
5) mm: expose ksm process profit metric and merge type in ksm_stat
This exposes the ksm process profit metric in /proc/<pid>/ksm_stat.
The name of the value is ksm_merge_type. The documentation mentions
the formula for the ksm process profit metric, however it does not
calculate it. In addition the formula depends on the size of internal
structures. So it makes sense to expose it.
6) document new procfs ksm knobs
Signed-off-by: Stefan Roesch <shr@xxxxxxxxxxxx>
Reviewed-by: Bagas Sanjaya <bagasdotme@xxxxxxxxx>
Cc: David Hildenbrand <david@xxxxxxxxxx>
Cc: Johannes Weiner <hannes@xxxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
Documentation/ABI/testing/sysfs-kernel-mm-ksm | 8 +++++
Documentation/admin-guide/mm/ksm.rst | 8 ++++-
fs/proc/base.c | 5 +++
include/linux/ksm.h | 5 +++
mm/ksm.c | 32 +++++++++++++++++++
5 files changed, 57 insertions(+), 1 deletion(-)
diff --git a/Documentation/ABI/testing/sysfs-kernel-mm-ksm b/Documentation/ABI/testing/sysfs-kernel-mm-ksm
index d244674a9480..7768e90f7a8f 100644
--- a/Documentation/ABI/testing/sysfs-kernel-mm-ksm
+++ b/Documentation/ABI/testing/sysfs-kernel-mm-ksm
@@ -51,3 +51,11 @@ Description: Control merging pages across different NUMA nodes.
When it is set to 0 only pages from the same node are merged,
otherwise pages from all nodes can be merged together (default).
+
+What: /sys/kernel/mm/ksm/general_profit
+Date: January 2023
+KernelVersion: 6.1
+Contact: Linux memory management mailing list <linux-mm@xxxxxxxxx>
+Description: Measure how effective KSM is.
+ general_profit: how effective is KSM. The formula for the
+ calculation is in Documentation/admin-guide/mm/ksm.rst.
diff --git a/Documentation/admin-guide/mm/ksm.rst b/Documentation/admin-guide/mm/ksm.rst
index 270560fef3b2..d2929964cd0f 100644
--- a/Documentation/admin-guide/mm/ksm.rst
+++ b/Documentation/admin-guide/mm/ksm.rst
@@ -157,6 +157,8 @@ stable_node_chains_prune_millisecs
The effectiveness of KSM and MADV_MERGEABLE is shown in ``/sys/kernel/mm/ksm/``:
+general_profit
+ how effective is KSM. The calculation is explained below.
pages_shared
how many shared pages are being used
pages_sharing
@@ -214,7 +216,8 @@ several times, which are unprofitable memory consumed.
ksm_rmap_items * sizeof(rmap_item).
where ksm_merging_pages is shown under the directory ``/proc/<pid>/``,
- and ksm_rmap_items is shown in ``/proc/<pid>/ksm_stat``.
+ and ksm_rmap_items is shown in ``/proc/<pid>/ksm_stat``. The process profit
+ is also shown in ``/proc/<pid>/ksm_stat`` as ksm_process_profit.
From the perspective of application, a high ratio of ``ksm_rmap_items`` to
``ksm_merging_pages`` means a bad madvise-applied policy, so developers or
@@ -225,6 +228,9 @@ so if the ``ksm_rmap_items/ksm_merging_pages`` ratio exceeds 64 on 64-bit CPU
or exceeds 128 on 32-bit CPU, then the app's madvise policy should be dropped,
because the ksm profit is approximately zero or negative.
+The ksm_merge_type in ``/proc/<pid>/ksm_stat`` shows the merge type of the
+process. Valid values are ``none``, ``madvise`` and ``process``.
+
Monitoring KSM events
=====================
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 07463ad4a70a..c74450318e05 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -96,6 +96,7 @@
#include <linux/time_namespace.h>
#include <linux/resctrl.h>
#include <linux/cn_proc.h>
+#include <linux/ksm.h>
#include <trace/events/oom.h>
#include "internal.h"
#include "fd.h"
@@ -3199,6 +3200,7 @@ static int proc_pid_ksm_merging_pages(struct seq_file *m, struct pid_namespace *
return 0;
}
+
static int proc_pid_ksm_stat(struct seq_file *m, struct pid_namespace *ns,
struct pid *pid, struct task_struct *task)
{
@@ -3208,6 +3210,9 @@ static int proc_pid_ksm_stat(struct seq_file *m, struct pid_namespace *ns,
if (mm) {
seq_printf(m, "ksm_rmap_items %lu\n", mm->ksm_rmap_items);
seq_printf(m, "zero_pages_sharing %lu\n", mm->ksm_zero_pages_sharing);
+ seq_printf(m, "ksm_merging_pages %lu\n", mm->ksm_merging_pages);
+ seq_printf(m, "ksm_merge_type %s\n", ksm_merge_type(mm));
+ seq_printf(m, "ksm_process_profit %ld\n", ksm_process_profit(mm));
mmput(mm);
}
diff --git a/include/linux/ksm.h b/include/linux/ksm.h
index c65455bf124c..4c32f9bca723 100644
--- a/include/linux/ksm.h
+++ b/include/linux/ksm.h
@@ -60,6 +60,11 @@ struct page *ksm_might_need_to_copy(struct page *page,
void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc);
void folio_migrate_ksm(struct folio *newfolio, struct folio *folio);
+#ifdef CONFIG_PROC_FS
+long ksm_process_profit(struct mm_struct *);
+const char *ksm_merge_type(struct mm_struct *mm);
+#endif /* CONFIG_PROC_FS */
+
#else /* !CONFIG_KSM */
static inline int ksm_add_mm(struct mm_struct *mm)
diff --git a/mm/ksm.c b/mm/ksm.c
index ab95ae0f9def..76b10ff840ac 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -3042,6 +3042,25 @@ static void wait_while_offlining(void)
}
#endif /* CONFIG_MEMORY_HOTREMOVE */
+#ifdef CONFIG_PROC_FS
+long ksm_process_profit(struct mm_struct *mm)
+{
+ return (long)mm->ksm_merging_pages * PAGE_SIZE -
+ mm->ksm_rmap_items * sizeof(struct ksm_rmap_item);
+}
+
+/* Return merge type name as string. */
+const char *ksm_merge_type(struct mm_struct *mm)
+{
+ if (test_bit(MMF_VM_MERGE_ANY, &mm->flags))
+ return "process";
+ else if (test_bit(MMF_VM_MERGEABLE, &mm->flags))
+ return "madvise";
+ else
+ return "none";
+}
+#endif /* CONFIG_PROC_FS */
+
#ifdef CONFIG_SYSFS
/*
* This all compiles without CONFIG_SYSFS, but is a waste of space.
@@ -3313,6 +3332,18 @@ static ssize_t zero_pages_sharing_show(struct kobject *kobj,
}
KSM_ATTR_RO(zero_pages_sharing);
+static ssize_t general_profit_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ long general_profit;
+
+ general_profit = ksm_pages_sharing * PAGE_SIZE -
+ ksm_rmap_items * sizeof(struct ksm_rmap_item);
+
+ return sysfs_emit(buf, "%ld\n", general_profit);
+}
+KSM_ATTR_RO(general_profit);
+
static ssize_t stable_node_dups_show(struct kobject *kobj,
struct kobj_attribute *attr, char *buf)
{
@@ -3378,6 +3409,7 @@ static struct attribute *ksm_attrs[] = {
&stable_node_dups_attr.attr,
&stable_node_chains_prune_millisecs_attr.attr,
&use_zero_pages_attr.attr,
+ &general_profit_attr.attr,
NULL,
};
--
2.34.1
