iv/linux
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs/vm: ksm: (mostly) formatting updates

Browse Source 
Aside from the formatting:
* fixed typos
* added section and sub-section headers
* moved ksmd overview after the description of KSM origins

Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com>
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
This commit is contained in:
Mike Rapoport 2018-04-24 09:40:23 +03:00 committed by Jonathan Corbet
parent 5a2ca3efe6
commit db12c00f13
1 changed files with 69 additions and 41 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

110
Documentation/vm/ksm.rst
View File

@ -4,34 +4,50 @@
Kernel Samepage Merging Kernel Samepage Merging
======================= =======================
Overview
========
KSM is a memory-saving de-duplication feature, enabled by CONFIG_KSM=y, KSM is a memory-saving de-duplication feature, enabled by CONFIG_KSM=y,
added to the Linux kernel in 2.6.32. See ``mm/ksm.c`` for its implementation, added to the Linux kernel in 2.6.32. See ``mm/ksm.c`` for its implementation,
and http://lwn.net/Articles/306704/ and http://lwn.net/Articles/330589/ and http://lwn.net/Articles/306704/ and http://lwn.net/Articles/330589/
The KSM daemon ksmd periodically scans those areas of user memory which
have been registered with it, looking for pages of identical content which
can be replaced by a single write-protected page (which is automatically
copied if a process later wants to update its content).
KSM was originally developed for use with KVM (where it was known as KSM was originally developed for use with KVM (where it was known as
Kernel Shared Memory), to fit more virtual machines into physical memory, Kernel Shared Memory), to fit more virtual machines into physical memory,
by sharing the data common between them. But it can be useful to any by sharing the data common between them. But it can be useful to any
application which generates many instances of the same data. application which generates many instances of the same data.
The KSM daemon ksmd periodically scans those areas of user memory
which have been registered with it, looking for pages of identical
content which can be replaced by a single write-protected page (which
is automatically copied if a process later wants to update its
content). The amount of pages that KSM daemon scans in a single pass
and the time between the passes are configured using :ref:`sysfs
intraface <ksm_sysfs>`
KSM only merges anonymous (private) pages, never pagecache (file) pages. KSM only merges anonymous (private) pages, never pagecache (file) pages.
KSM's merged pages were originally locked into kernel memory, but can now KSM's merged pages were originally locked into kernel memory, but can now
be swapped out just like other user pages (but sharing is broken when they be swapped out just like other user pages (but sharing is broken when they
are swapped back in: ksmd must rediscover their identity and merge again). are swapped back in: ksmd must rediscover their identity and merge again).
Controlling KSM with madvise
============================
KSM only operates on those areas of address space which an application KSM only operates on those areas of address space which an application
has advised to be likely candidates for merging, by using the madvise(2) has advised to be likely candidates for merging, by using the madvise(2)
system call: int madvise(addr, length, MADV_MERGEABLE). system call::
The app may call int madvise(addr, length, MADV_UNMERGEABLE) to cancel int madvise(addr, length, MADV_MERGEABLE)
that advice and restore unshared pages: whereupon KSM unmerges whatever
it merged in that range. Note: this unmerging call may suddenly require The app may call
more memory than is available - possibly failing with EAGAIN, but more
probably arousing the Out-Of-Memory killer. ::
int madvise(addr, length, MADV_UNMERGEABLE)
to cancel that advice and restore unshared pages: whereupon KSM
unmerges whatever it merged in that range. Note: this unmerging call
may suddenly require more memory than is available - possibly failing
with EAGAIN, but more probably arousing the Out-Of-Memory killer.
If KSM is not configured into the running kernel, madvise MADV_MERGEABLE If KSM is not configured into the running kernel, madvise MADV_MERGEABLE
and MADV_UNMERGEABLE simply fail with EINVAL. If the running kernel was and MADV_UNMERGEABLE simply fail with EINVAL. If the running kernel was
@ -43,7 +59,7 @@ MADV_UNMERGEABLE is applied to a range which was never MADV_MERGEABLE.
If a region of memory must be split into at least one new MADV_MERGEABLE If a region of memory must be split into at least one new MADV_MERGEABLE
or MADV_UNMERGEABLE region, the madvise may return ENOMEM if the process or MADV_UNMERGEABLE region, the madvise may return ENOMEM if the process
will exceed vm.max_map_count (see Documentation/sysctl/vm.txt). will exceed ``vm.max_map_count`` (see Documentation/sysctl/vm.txt).
Like other madvise calls, they are intended for use on mapped areas of Like other madvise calls, they are intended for use on mapped areas of
the user address space: they will report ENOMEM if the specified range the user address space: they will report ENOMEM if the specified range
@ -54,21 +70,28 @@ Applications should be considerate in their use of MADV_MERGEABLE,
restricting its use to areas likely to benefit. KSM's scans may use a lot restricting its use to areas likely to benefit. KSM's scans may use a lot
of processing power: some installations will disable KSM for that reason. of processing power: some installations will disable KSM for that reason.
.. _ksm_sysfs:
KSM daemon sysfs interface
==========================
The KSM daemon is controlled by sysfs files in ``/sys/kernel/mm/ksm/``, The KSM daemon is controlled by sysfs files in ``/sys/kernel/mm/ksm/``,
readable by all but writable only by root: readable by all but writable only by root:
pages_to_scan pages_to_scan
how many present pages to scan before ksmd goes to sleep how many pages to scan before ksmd goes to sleep
e.g. ``echo 100 > /sys/kernel/mm/ksm/pages_to_scan`` Default: 100 e.g. ``echo 100 > /sys/kernel/mm/ksm/pages_to_scan``.
(chosen for demonstration purposes)
Default: 100 (chosen for demonstration purposes)
sleep_millisecs sleep_millisecs
how many milliseconds ksmd should sleep before next scan how many milliseconds ksmd should sleep before next scan
e.g. ``echo 20 > /sys/kernel/mm/ksm/sleep_millisecs`` Default: 20 e.g. ``echo 20 > /sys/kernel/mm/ksm/sleep_millisecs``
(chosen for demonstration purposes)
Default: 20 (chosen for demonstration purposes)
merge_across_nodes merge_across_nodes
specifies if pages from different numa nodes can be merged. specifies if pages from different NUMA nodes can be merged.
When set to 0, ksm merges only pages which physically reside When set to 0, ksm merges only pages which physically reside
in the memory area of same NUMA node. That brings lower in the memory area of same NUMA node. That brings lower
latency to access of shared pages. Systems with more nodes, at latency to access of shared pages. Systems with more nodes, at
@ -77,19 +100,21 @@ merge_across_nodes
minimize memory usage, are likely to benefit from the greater minimize memory usage, are likely to benefit from the greater
sharing of setting 1 (default). You may wish to compare how sharing of setting 1 (default). You may wish to compare how
your system performs under each setting, before deciding on your system performs under each setting, before deciding on
which to use. merge_across_nodes setting can be changed only which to use. ``merge_across_nodes`` setting can be changed only
when there are no ksm shared pages in system: set run 2 to when there are no ksm shared pages in the system: set run 2 to
unmerge pages first, then to 1 after changing unmerge pages first, then to 1 after changing
merge_across_nodes, to remerge according to the new setting. ``merge_across_nodes``, to remerge according to the new setting.
Default: 1 (merging across nodes as in earlier releases) Default: 1 (merging across nodes as in earlier releases)
run run
set 0 to stop ksmd from running but keep merged pages, * set to 0 to stop ksmd from running but keep merged pages,
set 1 to run ksmd e.g. ``echo 1 > /sys/kernel/mm/ksm/run``, * set to 1 to run ksmd e.g. ``echo 1 > /sys/kernel/mm/ksm/run``,
set 2 to stop ksmd and unmerge all pages currently merged, but * set to 2 to stop ksmd and unmerge all pages currently merged, but
leave mergeable areas registered for next run Default: 0 (must leave mergeable areas registered for next run.
be changed to 1 to activate KSM, except if CONFIG_SYSFS is
disabled) Default: 0 (must be changed to 1 to activate KSM, except if
CONFIG_SYSFS is disabled)
use_zero_pages use_zero_pages
specifies whether empty pages (i.e. allocated pages that only specifies whether empty pages (i.e. allocated pages that only
@ -102,8 +127,9 @@ use_zero_pages
KSM for some workloads, for example if the checksums of pages KSM for some workloads, for example if the checksums of pages
candidate for merging match the checksum of an empty candidate for merging match the checksum of an empty
page. This setting can be changed at any time, it is only page. This setting can be changed at any time, it is only
effective for pages merged after the change. Default: 0 effective for pages merged after the change.
(normal KSM behaviour as in earlier releases)
Default: 0 (normal KSM behaviour as in earlier releases)
max_page_sharing max_page_sharing
Maximum sharing allowed for each KSM page. This enforces a Maximum sharing allowed for each KSM page. This enforces a
@ -112,7 +138,7 @@ max_page_sharing
page will have at least two sharers. The rmap walk has O(N) page will have at least two sharers. The rmap walk has O(N)
complexity where N is the number of rmap_items (i.e. virtual complexity where N is the number of rmap_items (i.e. virtual
mappings) that are sharing the page, which is in turn capped mappings) that are sharing the page, which is in turn capped
by max_page_sharing. So this effectively spread the the linear by ``max_page_sharing``. So this effectively spreads the linear
O(N) computational complexity from rmap walk context over O(N) computational complexity from rmap walk context over
different KSM pages. The ksmd walk over the stable_node different KSM pages. The ksmd walk over the stable_node
"chains" is also O(N), but N is the number of stable_node "chains" is also O(N), but N is the number of stable_node
@ -140,7 +166,7 @@ stable_node_chains_prune_millisecs
metadata with lower latency, but they will make ksmd use more metadata with lower latency, but they will make ksmd use more
CPU during the scan. This only applies to the stable_node CPU during the scan. This only applies to the stable_node
chains so it's a noop if not a single KSM page hit the chains so it's a noop if not a single KSM page hit the
max_page_sharing yet (there would be no stable_node chains in ``max_page_sharing`` yet (there would be no stable_node chains in
such case). such case).
The effectiveness of KSM and MADV_MERGEABLE is shown in ``/sys/kernel/mm/ksm/``: The effectiveness of KSM and MADV_MERGEABLE is shown in ``/sys/kernel/mm/ksm/``:
@ -157,27 +183,29 @@ full_scans
how many times all mergeable areas have been scanned how many times all mergeable areas have been scanned
stable_node_chains stable_node_chains
number of stable node chains allocated, this is effectively number of stable node chains allocated, this is effectively
the number of KSM pages that hit the max_page_sharing limit the number of KSM pages that hit the ``max_page_sharing`` limit
stable_node_dups stable_node_dups
number of stable node dups queued into the stable_node chains number of stable node dups queued into the stable_node chains
A high ratio of pages_sharing to pages_shared indicates good sharing, but A high ratio of ``pages_sharing`` to ``pages_shared`` indicates good
a high ratio of pages_unshared to pages_sharing indicates wasted effort. sharing, but a high ratio of ``pages_unshared`` to ``pages_sharing``
pages_volatile embraces several different kinds of activity, but a high indicates wasted effort. ``pages_volatile`` embraces several
proportion there would also indicate poor use of madvise MADV_MERGEABLE. different kinds of activity, but a high proportion there would also
indicate poor use of madvise MADV_MERGEABLE.
The maximum possible page_sharing/page_shared ratio is limited by the The maximum possible ``pages_sharing/pages_shared`` ratio is limited by the
max_page_sharing tunable. To increase the ratio max_page_sharing must ``max_page_sharing`` tunable. To increase the ratio ``max_page_sharing`` must
be increased accordingly. be increased accordingly.
The stable_node_dups/stable_node_chains ratio is also affected by the The ``stable_node_dups/stable_node_chains`` ratio is also affected by the
max_page_sharing tunable, and an high ratio may indicate fragmentation ``max_page_sharing`` tunable, and an high ratio may indicate fragmentation
in the stable_node dups, which could be solved by introducing in the stable_node dups, which could be solved by introducing
fragmentation algorithms in ksmd which would refile rmap_items from fragmentation algorithms in ksmd which would refile rmap_items from
one stable_node dup to another stable_node dup, in order to freeup one stable_node dup to another stable_node dup, in order to free up
stable_node "dups" with few rmap_items in them, but that may increase stable_node "dups" with few rmap_items in them, but that may increase
the ksmd CPU usage and possibly slowdown the readonly computations on the ksmd CPU usage and possibly slowdown the readonly computations on
the KSM pages of the applications. the KSM pages of the applications.
--
Izik Eidus, Izik Eidus,
Hugh Dickins, 17 Nov 2009 Hugh Dickins, 17 Nov 2009