!790 mm: enable ksm per process and cgroup (dcc34901) · Commits · EulixOS / Software / Kernel

Documentation/ABI/testing/sysfs-kernel-mm-ksm

+8 −0

Original line number	Diff line number	Diff line
		@@ -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.

Documentation/admin-guide/cgroup-v1/memory.rst

+1 −0

Original line number	Diff line number	Diff line
		@@ -99,6 +99,7 @@ Brief summary of control files.
		memory.kmem.tcp.failcnt show the number of tcp buf memory usage
		hits limits
		memory.kmem.tcp.max_usage_in_bytes show max tcp buf memory usage recorded
		memory.ksm set/show ksm merge any mode
		==================================== ==========================================

		1. History

Documentation/admin-guide/mm/ksm.rst

+40 −0

Original line number	Diff line number	Diff line
		@@ -159,6 +159,8 @@ 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
		@@ -184,6 +186,44 @@ The maximum possible ``pages_sharing/pages_shared`` ratio is limited by the
		``max_page_sharing`` tunable. To increase the ratio ``max_page_sharing`` must
		be increased accordingly.


		Monitoring KSM profit
		=====================

		KSM can save memory by merging identical pages, but also can consume
		additional memory, because it needs to generate a number of 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.

		1) How to determine whether KSM save memory or consume memory in system-wide
		range? Here is a simple approximate calculation for reference::

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

		where all_rmap_items can be easily obtained by summing ``pages_sharing``,
		``pages_shared``, ``pages_unshared`` and ``pages_volatile``.

		2) The KSM profit inner a single process can be similarly obtained by the
		following approximate calculation::

		process_profit =~ ksm_merging_pages * sizeof(page) -
		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``. 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
		administrators have to rethink how to change madvise policy. Giving an example
		for reference, a page's size is usually 4K, and the rmap_item's size is
		separately 32B on 32-bit CPU architecture and 64B on 64-bit CPU architecture.
		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.

		--
		Izik Eidus,
		Hugh Dickins, 17 Nov 2009

arch/s390/mm/gmap.c

+7 −0

Original line number	Diff line number	Diff line
		@@ -2573,6 +2573,13 @@ int gmap_mark_unmergeable(void)
		struct vm_area_struct *vma;
		int ret;

		/*
		* Make sure to disable KSM (if enabled for the whole process or
		* individual VMAs). Note that nothing currently hinders user space
		* from re-enabling it.
		*/
		clear_bit(MMF_VM_MERGE_ANY, &mm->flags);

		for (vma = mm->mmap; vma; vma = vma->vm_next) {
		ret = ksm_madvise(vma, vma->vm_start, vma->vm_end,
		MADV_UNMERGEABLE, &vma->vm_flags);

fs/proc/base.c

+40 −0

Original line number	Diff line number	Diff line
		@@ -97,6 +97,7 @@
		#include <linux/time_namespace.h>
		#include <linux/resctrl.h>
		#include <linux/share_pool.h>
		#include <linux/ksm.h>
		#include <trace/events/oom.h>
		#include "internal.h"
		#include "fd.h"
		@@ -3341,6 +3342,37 @@ static int proc_pid_patch_state(struct seq_file m, struct pid_namespace ns,
		}
		#endif /* CONFIG_LIVEPATCH */

		#ifdef CONFIG_KSM
		static int proc_pid_ksm_merging_pages(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_merging_pages);
		mmput(mm);
		}

		return 0;
		}
		static int proc_pid_ksm_stat(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, "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);
		}

		return 0;
		}
		#endif /* CONFIG_KSM */

		#ifdef CONFIG_STACKLEAK_METRICS
		static int proc_stack_depth(struct seq_file m, struct pid_namespace ns,
		struct pid pid, struct task_struct task)
		@@ -3482,6 +3514,10 @@ static const struct pid_entry tgid_base_stuff[] = {
		#ifdef CONFIG_ASCEND_SHARE_POOL
		ONE("sp_group", 0444, proc_sp_group_state),
		#endif
		#ifdef CONFIG_KSM
		ONE("ksm_merging_pages", S_IRUSR, proc_pid_ksm_merging_pages),
		ONE("ksm_stat", S_IRUSR, proc_pid_ksm_stat),
		#endif
		};

		static int proc_tgid_base_readdir(struct file file, struct dir_context ctx)
		@@ -3893,6 +3929,10 @@ static const struct pid_entry tid_base_stuff[] = {
		#ifdef CONFIG_QOS_SCHED_DYNAMIC_AFFINITY
		REG("preferred_cpuset", 0644, proc_preferred_cpuset_operations),
		#endif
		#ifdef CONFIG_KSM
		ONE("ksm_merging_pages", S_IRUSR, proc_pid_ksm_merging_pages),
		ONE("ksm_stat", S_IRUSR, proc_pid_ksm_stat),
		#endif
		};

		static int proc_tid_base_readdir(struct file file, struct dir_context ctx)