Both Ryan and Chris have been utilizing the small test program to aid in
debugging and identifying issues with swap entry allocation. While a real
or intricate workload might be more suitable for assessing the correctness
and effectiveness of the swap allocation policy, a small test program
presents a simpler means of understanding the problem and initially
verifying the improvements being made.
Let's endeavor to integrate it into tools/mm. Although it presently only
accommodates 64KB and 4KB, I'm optimistic that we can expand its
capabilities to support multiple sizes and simulate more complex systems
in the future as required.
Basically, we have
1. Use MADV_PAGEPUT for rapid swap-out, putting the swap allocation
code under high exercise in a short time.
2. Use MADV_DONTNEED to simulate the behavior of libc and Java heap in
freeing memory, as well as for munmap, app exits, or OOM killer
scenarios. This ensures new mTHP is always generated, released or
swapped out, similar to the behavior on a PC or Android phone where
many applications are frequently started and terminated.
3. Swap in with or without the "-a" option to observe how fragments
due to swap-in and the incoming swap-in of large folios will impact
swap-out fallback.
Due to 2, we ensure a certain proportion of mTHP. Similarly, because of
3, we maintain a certain proportion of small folios, as we don't support
large folios swap-in, meaning any swap-in will immediately result in small
folios. Therefore, with both 2 and 3, we automatically achieve a system
containing both mTHP and small folios. Additionally, 1 provides the
ability to continuously swap them out.
We can also use "-s" to add a dedicated small folios memory area.
[akpm@linux-foundation.org: thp_swap_allocator_test.c needs mman.h, per Kairui Song]
Link: https://lkml.kernel.org/r/20240622071231.576056-2-21cnbao@gmail.com
Signed-off-by: Barry Song <v-songbaohua@oppo.com>
Acked-by: Chris Li <chrisl@kernel.org>
Tested-by: Chris Li <chrisl@kernel.org>
Reviewed-by: Ryan Roberts <ryan.roberts@arm.com>
Tested-by: Ryan Roberts <ryan.roberts@arm.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: "Huang, Ying" <ying.huang@intel.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Kairui Song <kasong@tencent.com>
Cc: Kalesh Singh <kaleshsingh@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
With the proliferation of large folios for file-backed memory, and more
recently the introduction of multi-size THP for anonymous memory, it is
becoming useful to be able to see exactly how large folios are mapped into
processes. For some architectures (e.g. arm64), if most memory is mapped
using contpte-sized and -aligned blocks, TLB usage can be optimized so
it's useful to see where these requirements are and are not being met.
thpmaps is a Python utility that reads /proc/<pid>/smaps,
/proc/<pid>/pagemap and /proc/kpageflags to print information about how
transparent huge pages (both file and anon) are mapped to a specified
process or cgroup. It aims to help users debug and optimize their
workloads. In future we may wish to introduce stats directly into the
kernel (e.g. smaps or similar), but for now this provides a short term
solution without the need to introduce any new ABI.
Run with help option for a full listing of the arguments:
# ./thpmaps --help
--8<--
usage: thpmaps [-h] [--pid pid | --cgroup path] [--rollup]
[--cont size[KMG]] [--inc-smaps] [--inc-empty]
[--periodic sleep_ms]
Prints information about how transparent huge pages are mapped, either
system-wide, or for a specified process or cgroup.
When run with --pid, the user explicitly specifies the set of pids to
scan. e.g. "--pid 10 [--pid 134 ...]". When run with --cgroup, the user
passes either a v1 or v2 cgroup and all pids that belong to the cgroup
subtree are scanned. When run with neither --pid nor --cgroup, the full
set of pids on the system is gathered from /proc and scanned as if the
user had provided "--pid 1 --pid 2 ...".
A default set of statistics is always generated for THP mappings.
However, it is also possible to generate additional statistics for
"contiguous block mappings" where the block size is user-defined.
Statistics are maintained independently for anonymous and file-backed
(pagecache) memory and are shown both in kB and as a percentage of either
total anonymous or total file-backed memory as appropriate.
THP Statistics
--------------
Statistics are always generated for fully- and contiguously-mapped THPs
whose mapping address is aligned to their size, for each <size> supported
by the system. Separate counters describe THPs mapped by PTE vs those
mapped by PMD. (Although note a THP can only be mapped by PMD if it is
PMD-sized):
- anon-thp-pte-aligned-<size>kB
- file-thp-pte-aligned-<size>kB
- anon-thp-pmd-aligned-<size>kB
- file-thp-pmd-aligned-<size>kB
Similarly, statistics are always generated for fully- and contiguously-
mapped THPs whose mapping address is *not* aligned to their size, for each
<size> supported by the system. Due to the unaligned mapping, it is
impossible to map by PMD, so there are only PTE counters for this case:
- anon-thp-pte-unaligned-<size>kB
- file-thp-pte-unaligned-<size>kB
Statistics are also always generated for mapped pages that belong to a THP
but where the is THP is *not* fully- and contiguously- mapped. These
"partial" mappings are all counted in the same counter regardless of the
size of the THP that is partially mapped:
- anon-thp-pte-partial
- file-thp-pte-partial
Contiguous Block Statistics
---------------------------
An optional, additional set of statistics is generated for every
contiguous block size specified with `--cont <size>`. These statistics
show how much memory is mapped in contiguous blocks of <size> and also
aligned to <size>. A given contiguous block must all belong to the same
THP, but there is no requirement for it to be the *whole* THP. Separate
counters describe contiguous blocks mapped by PTE vs those mapped by PMD:
- anon-cont-pte-aligned-<size>kB
- file-cont-pte-aligned-<size>kB
- anon-cont-pmd-aligned-<size>kB
- file-cont-pmd-aligned-<size>kB
As an example, if monitoring 64K contiguous blocks (--cont 64K), there are
a number of sources that could provide such blocks: a fully- and
contiguously-mapped 64K THP that is aligned to a 64K boundary would
provide 1 block. A fully- and contiguously-mapped 128K THP that is
aligned to at least a 64K boundary would provide 2 blocks. Or a 128K THP
that maps its first 100K, but contiguously and starting at a 64K boundary
would provide 1 block. A fully- and contiguously-mapped 2M THP would
provide 32 blocks. There are many other possible permutations.
options:
-h, --help show this help message and exit
--pid pid Process id of the target process. Maybe issued
multiple times to scan multiple processes. --pid
and --cgroup are mutually exclusive. If neither
are provided, all processes are scanned to
provide system-wide information.
--cgroup path Path to the target cgroup in sysfs. Iterates
over every pid in the cgroup and its children.
--pid and --cgroup are mutually exclusive. If
neither are provided, all processes are scanned
to provide system-wide information.
--rollup Sum the per-vma statistics to provide a summary
over the whole system, process or cgroup.
--cont size[KMG] Adds stats for memory that is mapped in
contiguous blocks of <size> and also aligned to
<size>. May be issued multiple times to track
multiple sized blocks. Useful to infer e.g.
arm64 contpte and hpa mappings. Size must be a
power-of-2 number of pages.
--inc-smaps Include all numerical, additive
/proc/<pid>/smaps stats in the output.
--inc-empty Show all statistics including those whose value
is 0.
--periodic sleep_ms Run in a loop, polling every sleep_ms
milliseconds.
Requires root privilege to access pagemap and kpageflags.
--8<--
Example command to summarise fully and partially mapped THPs and 64K
contiguous blocks over all VMAs in all processes in the system
(--inc-empty forces printing stats that are 0):
# ./thpmaps --cont 64K --rollup --inc-empty
--8<--
anon-thp-pmd-aligned-2048kB: 139264 kB ( 6%)
file-thp-pmd-aligned-2048kB: 0 kB ( 0%)
anon-thp-pte-aligned-16kB: 0 kB ( 0%)
anon-thp-pte-aligned-32kB: 0 kB ( 0%)
anon-thp-pte-aligned-64kB: 72256 kB ( 3%)
anon-thp-pte-aligned-128kB: 0 kB ( 0%)
anon-thp-pte-aligned-256kB: 0 kB ( 0%)
anon-thp-pte-aligned-512kB: 0 kB ( 0%)
anon-thp-pte-aligned-1024kB: 0 kB ( 0%)
anon-thp-pte-aligned-2048kB: 0 kB ( 0%)
anon-thp-pte-unaligned-16kB: 0 kB ( 0%)
anon-thp-pte-unaligned-32kB: 0 kB ( 0%)
anon-thp-pte-unaligned-64kB: 0 kB ( 0%)
anon-thp-pte-unaligned-128kB: 0 kB ( 0%)
anon-thp-pte-unaligned-256kB: 0 kB ( 0%)
anon-thp-pte-unaligned-512kB: 0 kB ( 0%)
anon-thp-pte-unaligned-1024kB: 0 kB ( 0%)
anon-thp-pte-unaligned-2048kB: 0 kB ( 0%)
anon-thp-pte-partial: 63232 kB ( 3%)
file-thp-pte-aligned-16kB: 809024 kB (47%)
file-thp-pte-aligned-32kB: 43168 kB ( 3%)
file-thp-pte-aligned-64kB: 98496 kB ( 6%)
file-thp-pte-aligned-128kB: 17536 kB ( 1%)
file-thp-pte-aligned-256kB: 0 kB ( 0%)
file-thp-pte-aligned-512kB: 0 kB ( 0%)
file-thp-pte-aligned-1024kB: 0 kB ( 0%)
file-thp-pte-aligned-2048kB: 0 kB ( 0%)
file-thp-pte-unaligned-16kB: 21712 kB ( 1%)
file-thp-pte-unaligned-32kB: 704 kB ( 0%)
file-thp-pte-unaligned-64kB: 896 kB ( 0%)
file-thp-pte-unaligned-128kB: 44928 kB ( 3%)
file-thp-pte-unaligned-256kB: 0 kB ( 0%)
file-thp-pte-unaligned-512kB: 0 kB ( 0%)
file-thp-pte-unaligned-1024kB: 0 kB ( 0%)
file-thp-pte-unaligned-2048kB: 0 kB ( 0%)
file-thp-pte-partial: 9252 kB ( 1%)
anon-cont-pmd-aligned-64kB: 139264 kB ( 6%)
file-cont-pmd-aligned-64kB: 0 kB ( 0%)
anon-cont-pte-aligned-64kB: 100672 kB ( 4%)
file-cont-pte-aligned-64kB: 161856 kB ( 9%)
--8<--
Link: https://lkml.kernel.org/r/20240116141235.960842-1-ryan.roberts@arm.com
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
Tested-by: Barry Song <v-songbaohua@oppo.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: William Kucharski <william.kucharski@oracle.com>
Cc: Zenghui Yu <yuzenghui@huawei.com>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Organize the usage options alphabetically and improve the description of
some options. Also separate the more complicated cull options from the
single use compare options.
Link: https://lkml.kernel.org/r/20231013190350.579407-6-audra@redhat.com
Signed-off-by: Audra Mitchell <audra@redhat.com>
Acked-by: Rafael Aquini <aquini@redhat.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Georgi Djakov <djakov@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
With the additional commands and timestamps added to the tool, the default
case (-t) has been broken. Now that the allocation timestamps are saved
outside of the txt field, allow us to properly sort the data by number of
times the record has been seen. Furthermore prevent the misuse of the
commandline arguments so only one compare option can be used.
Link: https://lkml.kernel.org/r/20231013190350.579407-5-audra@redhat.com
Signed-off-by: Audra Mitchell <audra@redhat.com>
Acked-by: Rafael Aquini <aquini@redhat.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Georgi Djakov <djakov@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
With the introduction of allocation timestamps being included in
page_owner output, each record becomes unique due to the timestamp
nanosecond granularity. Remove the check in add_list that tries to
collate each record during processing as the memcmp() is just additional
overhead at this point.
Also keep the allocation timestamps, but allow collation to occur without
consideration of the allocation timestamp except in the case were
allocation timestamps are requested by the user (the -a option).
Link: https://lkml.kernel.org/r/20231013190350.579407-4-audra@redhat.com
Signed-off-by: Audra Mitchell <audra@redhat.com>
Acked-by: Rafael Aquini <aquini@redhat.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Georgi Djakov <djakov@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
With the removal of free timestamps from page_owner output, we no longer
need to handle this case or the "unreleased" case. Remove all references
to both cases.
Link: https://lkml.kernel.org/r/20231013190350.579407-3-audra@redhat.com
Signed-off-by: Audra Mitchell <audra@redhat.com>
Acked-by: Rafael Aquini <aquini@redhat.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Georgi Djakov <djakov@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Commit 97d5f2e9ee ("tools api fs: More thread safety for global
filesystem variables") introduces pthread_once, so the libpthread
should be added at link time, or we'll meet the following compile
error when 'make -C tools/mm':
gcc -Wall -Wextra -I../lib/ -o page-types page-types.c ../lib/api/libapi.a
~/linux/tools/lib/api/fs/fs.c:146: undefined reference to `pthread_once'
~/linux/tools/lib/api/fs/fs.c:147: undefined reference to `pthread_once'
~/linux/tools/lib/api/fs/fs.c:148: undefined reference to `pthread_once'
~/linux/tools/lib/api/fs/fs.c:149: undefined reference to `pthread_once'
~/linux/tools/lib/api/fs/fs.c:150: undefined reference to `pthread_once'
/usr/bin/ld: ../lib/api/libapi.a(libapi-in.o):~/linux/tools/lib/api/fs/fs.c:151:
more undefined references to `pthread_once' follow
collect2: error: ld returned 1 exit status
make: *** [Makefile:22: page-types] Error 1
Link: https://lkml.kernel.org/r/20230831034205.2376653-1-xiexiuqi@huaweicloud.com
Fixes: 97d5f2e9ee ("tools api fs: More thread safety for global filesystem variables")
Signed-off-by: Xie XiuQi <xiexiuqi@huawei.com>
Acked-by: Ian Rogers <irogers@google.com>
Cc: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
-----BEGIN PGP SIGNATURE-----
iQEzBAABCAAdFiEEe7vIQRWZI0iWSE3xu+CwddJFiJoFAmRCSGEACgkQu+CwddJF
iJpA2wgAkwMP++Znd8JU3iQ4N53lv18euNuEMLTOY+jk7zXHvsRX8KyzLmsohUKO
SSGVi1Om785AidOsJhARJawW7AWYuJ5l7ri+FyskTwrTUcMC4UZ/IT2tB22lRsXi
0f3lgbdArZbj7aq7AVO9N7bh9rgVUHa/RHIwXzMp0sc9nekne9t+FFv7tyRnr7cc
SMp/FdMZqbt9pVf0Uwud1BpdgER7QqQaSfaxITL7D2oJTePRZVWiXerrr4hMcQl1
s6kgUgKdlaYmIx2N8eP1Nmp7undtwHo1C8dLLWKGCEuEAaXIxtXUtaUWFFmBDzH9
Fv6qswNFcfwiLNPsY+xi9iA+vlGKAg==
=T0EM
-----END PGP SIGNATURE-----
Merge tag 'slab-for-6.4' of git://git.kernel.org/pub/scm/linux/kernel/git/vbabka/slab
Pull slab updates from Vlastimil Babka:
"The main change is naturally the SLOB removal. Since its deprecation
in 6.2 I've seen no complaints so hopefully SLUB_(TINY) works well for
everyone and we can proceed.
Besides the code cleanup, the main immediate benefit will be allowing
kfree() family of function to work on kmem_cache_alloc() objects,
which was incompatible with SLOB. This includes kfree_rcu() which had
no kmem_cache_free_rcu() counterpart yet and now it shouldn't be
necessary anymore.
Besides that, there are several small code and comment improvements
from Thomas, Thorsten and Vernon"
* tag 'slab-for-6.4' of git://git.kernel.org/pub/scm/linux/kernel/git/vbabka/slab:
mm/slab: document kfree() as allowed for kmem_cache_alloc() objects
mm/slob: remove slob.c
mm/slab: remove CONFIG_SLOB code from slab common code
mm, pagemap: remove SLOB and SLQB from comments and documentation
mm, page_flags: remove PG_slob_free
mm/slob: remove CONFIG_SLOB
mm/slub: fix help comment of SLUB_DEBUG
mm: slub: make kobj_type structure constant
slab: Adjust comment after refactoring of gfp.h
When using cull option with 'tg' flag, the fprintf is using pid instead
of tgid. It should use tgid instead.
Link: https://lkml.kernel.org/r/20230411034929.2071501-1-steve_chou@pesi.com.tw
Fixes: 9c8a0a8e59 ("tools/vm/page_owner_sort.c: support for user-defined culling rules")
Signed-off-by: Steve Chou <steve_chou@pesi.com.tw>
Cc: Jiajian Ye <yejiajian2018@email.szu.edu.cn>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
With SLOB removed we no longer need the PG_slob_free alias for
PG_private. Also update tools/mm/page-types.
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Acked-by: Lorenzo Stoakes <lstoakes@gmail.com>
Acked-by: Mike Rapoport (IBM) <rppt@kernel.org>
Right now there is no way to provide additional cflags/ldflags when
building tools/vm binaries. And using eg. make CFLAGS=<options> will
override the CFLAGS being set in the Makefile, making the build fail since
it requires the include of the ../lib dir (for libapi).
This change then allows you to specify:
CFLAGS=<options> LDFLAGS=<options> make V=1 -C tools/vm
And the options will be correctly appended as can be seen from the
make output.
Link: https://lkml.kernel.org/r/20230116224921.4106324-1-herton@redhat.com
Signed-off-by: Herton R. Krzesinski <herton@redhat.com>
Cc: Don Zickus <dzickus@redhat.com>
Cc: Justin Forbes <jforbes@redhat.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Scott Weaver <scweaver@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Rename tools/vm to tools/mm for being more consistent with the code and
documentation directories, and won't be confused with virtual machines.
Link: https://lkml.kernel.org/r/20230103180754.129637-4-sj@kernel.org
Signed-off-by: SeongJae Park <sj@kernel.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Shuah Khan <shuah@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
