mm: add new KSM process and sysfs knobs

This adds the general_profit KSM sysfs knob and the process profit metric
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) mm: expose ksm process profit metric in ksm_stat

   This exposes the ksm process profit metric in /proc/<pid>/ksm_stat.
   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.

5) document new procfs ksm knobs

Link: https://lkml.kernel.org/r/20230418051342.1919757-3-shr@devkernel.io
Signed-off-by: Stefan Roesch <shr@devkernel.io>
Reviewed-by: Bagas Sanjaya <bagasdotme@gmail.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Rik van Riel <riel@surriel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/Documentation/ABI/testing/sysfs-kernel-mm-ksm b/Documentation/ABI/testing/sysfs-kernel-mm-ksm
index d244674a94806460c61e0afe4f12846a28ab52e3..6041a025b65a382bf6a42124039c658d075af0c9 100644 (file)
--- 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:          April 2023
+KernelVersion:  6.4
+Contact:       Linux memory management mailing list <linux-mm@kvack.org>
+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 eed51a910c940e19b295eeb3825422a29f6aa39d..551083a396fbd6e7cf7be011852c85f8646ed2e2 100644 (file)
--- 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
@@ -207,7 +209,8 @@ 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

diff --git a/fs/proc/base.c b/fs/proc/base.c
index 5e0e0ccd47aa760190f75d14d8128264ba0a1b26..96a6a08c8235bbfe9db0ec0f5e892fe919493f52 100644 (file)
--- 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"
@@ -3207,6 +3208,8 @@ static int proc_pid_ksm_stat(struct seq_file *m, struct pid_namespace *ns,
        mm = get_task_mm(task);
        if (mm) {
                seq_printf(m, "ksm_rmap_items %lu\n", mm->ksm_rmap_items);
+               seq_printf(m, "ksm_merging_pages %lu\n", mm->ksm_merging_pages);
+               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 4647b0c70c120a453b89932b8cc003a3ad0e01a2..7a9b76fb6c3f721686f9eee1e0f38a3c17ea74b6 100644 (file)
--- a/include/linux/ksm.h
+++ b/include/linux/ksm.h
@@ -68,6 +68,11 @@ void folio_migrate_ksm(struct folio *newfolio, struct folio *folio);
 void collect_procs_ksm(struct page *page, struct list_head *to_kill,
                       int force_early);
 #endif
+
+#ifdef CONFIG_PROC_FS
+long ksm_process_profit(struct mm_struct *);
+#endif /* CONFIG_PROC_FS */
+
 #else  /* !CONFIG_KSM */
 
 static inline void ksm_add_vma(struct vm_area_struct *vma)

diff --git a/mm/ksm.c b/mm/ksm.c
index 35ac6c741572e96c5448ab1f0bc0967215bce6d9..9e48258985d2f42ec3acd62787378e813eee3d4c 100644 (file)
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -3007,6 +3007,14 @@ static void wait_while_offlining(void)
 }
 #endif /* CONFIG_MEMORY_HOTREMOVE */
 
+#ifdef CONFIG_PROC_FS
+long ksm_process_profit(struct mm_struct *mm)
+{
+       return mm->ksm_merging_pages * PAGE_SIZE -
+               mm->ksm_rmap_items * sizeof(struct ksm_rmap_item);
+}
+#endif /* CONFIG_PROC_FS */
+
 #ifdef CONFIG_SYSFS
 /*
  * This all compiles without CONFIG_SYSFS, but is a waste of space.
@@ -3271,6 +3279,18 @@ static ssize_t pages_volatile_show(struct kobject *kobj,
 }
 KSM_ATTR_RO(pages_volatile);
 
+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)
 {
@@ -3335,6 +3355,7 @@ 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,
 };