The rmap locks(i_mmap_rwsem and anon_vma->root->rwsem) could be contended
under memory pressure if processes keep working on their vmas(e.g., fork,
mmap, munmap). It makes reclaim path stuck. In our real workload traces,
we see kswapd is waiting the lock for 300ms+(worst case, a sec) and it
makes other processes entering direct reclaim, which were also stuck on
the lock.
This patch makes lru aging path try_lock mode like shink_page_list so the
reclaim context will keep working with next lru pages without being stuck.
if it found the rmap lock contended, it rotates the page back to head of
lru in both active/inactive lrus to make them consistent behavior, which
is basic starting point rather than adding more heristic.
Since this patch introduces a new "contended" field as out-param along
with try_lock in-param in rmap_walk_control, it's not immutable any longer
if the try_lock is set so remove const keywords on rmap related functions.
Since rmap walking is already expensive operation, I doubt the const
would help sizable benefit( And we didn't have it until 5.17).
In a heavy app workload in Android, trace shows following statistics. It
almost removes rmap lock contention from reclaim path.
Martin Liu reported:
Before:
max_dur(ms) min_dur(ms) max-min(dur)ms avg_dur(ms) sum_dur(ms) count blocked_function
1632 0 1631 151.542173 31672 209 page_lock_anon_vma_read
601 0 601 145.544681 28817 198 rmap_walk_file
After:
max_dur(ms) min_dur(ms) max-min(dur)ms avg_dur(ms) sum_dur(ms) count blocked_function
NaN NaN NaN NaN NaN 0.0 NaN
0 0 0 0.127645 1 12 rmap_walk_file
[minchan@kernel.org: add comment, per Matthew]
Link: https://lkml.kernel.org/r/YnNqeB5tUf6LZ57b@google.com
Link: https://lkml.kernel.org/r/20220510215423.164547-1-minchan@kernel.org
Signed-off-by: Minchan Kim <minchan@kernel.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: John Dias <joaodias@google.com>
Cc: Tim Murray <timmurray@google.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Martin Liu <liumartin@google.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Applications can currently escape their cgroup memory containment when
zswap is enabled. This patch adds per-cgroup tracking and limiting of
zswap backend memory to rectify this.
The existing cgroup2 memory.stat file is extended to show zswap statistics
analogous to what's in meminfo and vmstat. Furthermore, two new control
files, memory.zswap.current and memory.zswap.max, are added to allow
tuning zswap usage on a per-workload basis. This is important since not
all workloads benefit from zswap equally; some even suffer compared to
disk swap when memory contents don't compress well. The optimal size of
the zswap pool, and the threshold for writeback, also depends on the size
of the workload's warm set.
The implementation doesn't use a traditional page_counter transaction.
zswap is unconventional as a memory consumer in that we only know the
amount of memory to charge once expensive compression has occurred. If
zwap is disabled or the limit is already exceeded we obviously don't want
to compress page upon page only to reject them all. Instead, the limit is
checked against current usage, then we compress and charge. This allows
some limit overrun, but not enough to matter in practice.
[hannes@cmpxchg.org: fix for CONFIG_SLOB builds]
Link: https://lkml.kernel.org/r/YnwD14zxYjUJPc2w@cmpxchg.org
[hannes@cmpxchg.org: opt out of cgroups v1]
Link: https://lkml.kernel.org/r/Yn6it9mBYFA+/lTb@cmpxchg.org
Link: https://lkml.kernel.org/r/20220510152847.230957-7-hannes@cmpxchg.org
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Roman Gushchin <guro@fb.com>
Cc: Shakeel Butt <shakeelb@google.com>
Cc: Seth Jennings <sjenning@redhat.com>
Cc: Dan Streetman <ddstreet@ieee.org>
Cc: Minchan Kim <minchan@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
- CONFIG_ZRAM: Zram is a user-facing feature, whereas zsmalloc is
not. Don't make the user chase down a technical dependency like
that, just select it in automatically when zram is requested. The
CONFIG_CRYPTO dependency is redundant due to more specific deps.
- CONFIG_ZPOOL: This is not a user-facing feature. Hide the symbol and
have it selected in as needed.
- CONFIG_ZSWAP: Select CRYPTO instead of depend. Common pattern.
- Make the ZSWAP suboptions and their descriptions (compression,
allocation backend) a bit more straight-forward for the user.
Link: https://lkml.kernel.org/r/20220510152847.230957-5-hannes@cmpxchg.org
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Dan Streetman <ddstreet@ieee.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Roman Gushchin <guro@fb.com>
Cc: Seth Jennings <sjenning@redhat.com>
Cc: Shakeel Butt <shakeelb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Patch series "zswap: accounting & cgroup control", v2.
Zswap can consume nearly a quarter of RAM in the default configuration,
yet it's neither listed in /proc/meminfo, nor is it accounted and
manageable on a per-cgroup basis.
This makes reasoning about the memory situation on a host in general
rather difficult. On shared/cgrouped hosts, the consequences are worse.
First, workloads can escape memory containment and cause resource priority
inversions: a lo-pri group can fill the global zswap pool and force a
hi-pri group out to disk. Second, not all workloads benefit from zswap
equally. Some even suffer when memory contents compress poorly, and are
better off going to disk swap directly. On a host with mixed workloads,
it's currently not possible to enable zswap for one workload but not for
the other.
This series implements the missing global accounting as well as cgroup
tracking & control for zswap backing memory:
- Patch 1 refreshes the very out-of-date meminfo documentation in
Documentation/filesystems/proc.rst.
- Patches 2-4 clean up related and adjacent options in Kconfig. Not
actual dependencies, just things I noticed during development.
- Patch 5 adds meminfo and vmstat coverage for zswap consumption and
activity.
- Patch 6 implements per-cgroup tracking & control of zswap memory.
This patch (of 6):
Add new entries. Minor corrections and cleanups.
[hannes@cmpxchg.org: fix htmldocs warnings]
Link: https://lkml.kernel.org/r/Ynve8dg4zJyhH2gW@cmpxchg.org
[hannes@cmpxchg.org: change `Unevictable' wording, per David]
Link: https://lkml.kernel.org/r/YnwFraZlVWQoCjz3@cmpxchg.org
Link: https://lkml.kernel.org/r/20220510152847.230957-1-hannes@cmpxchg.org
Link: https://lkml.kernel.org/r/20220510152847.230957-2-hannes@cmpxchg.org
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Dan Streetman <ddstreet@ieee.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Roman Gushchin <guro@fb.com>
Cc: Seth Jennings <sjenning@redhat.com>
Cc: Shakeel Butt <shakeelb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
The readonly FS THP relies on khugepaged to collapse THP for suitable
vmas. But the behavior is inconsistent for "always" mode
(https://lore.kernel.org/linux-mm/00f195d4-d039-3cf2-d3a1-a2c88de397a0@suse.cz/).
The "always" mode means THP allocation should be tried all the time and
khugepaged should try to collapse THP all the time. Of course the
allocation and collapse may fail due to other factors and conditions.
Currently file THP may not be collapsed by khugepaged even though all the
conditions are met. That does break the semantics of "always" mode.
So make sure readonly FS vmas are registered to khugepaged to fix the
break.
Register suitable vmas in common mmap path, that could cover both readonly
FS vmas and shmem vmas, so remove the khugepaged calls in shmem.c.
Still need to keep the khugepaged call in vma_merge() since vma_merge() is
called in a lot of places, for example, madvise, mprotect, etc.
Link: https://lkml.kernel.org/r/20220510203222.24246-9-shy828301@gmail.com
Signed-off-by: Yang Shi <shy828301@gmail.com>
Reported-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Vlastmil Babka <vbabka@suse.cz>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Song Liu <songliubraving@fb.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Zi Yan <ziy@nvidia.com>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: Song Liu <song@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
We run a lot of automated tests when building our software and run into
OOM scenarios when the tests run unbounded. v1 memcg exports
memcg->watermark as "memory.max_usage_in_bytes" in sysfs. We use this
metric to heuristically limit the number of tests that can run in parallel
based on per test historical data.
This metric is currently not exported for v2 memcg and there is no other
easy way of getting this information. getrusage() syscall returns
"ru_maxrss" which can be used as an approximation but that's the max RSS
of a single child process across all children instead of the aggregated
max for all child processes. The only work around is to periodically poll
"memory.current" but that's not practical for short-lived one-off cgroups.
Hence, expose memcg->watermark as "memory.peak" for v2 memcg.
Link: https://lkml.kernel.org/r/20220507050916.GA13577@us192.sjc.aristanetworks.com
Signed-off-by: Ganesan Rajagopal <rganesan@arista.com>
Acked-by: Shakeel Butt <shakeelb@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Roman Gushchin <roman.gushchin@linux.dev>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Reviewed-by: Michal Koutný <mkoutny@suse.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
We must add hugetlb_free_vmemmap=on (or "off") to the boot cmdline and
reboot the server to enable or disable the feature of optimizing vmemmap
pages associated with HugeTLB pages. However, rebooting usually takes a
long time. So add a sysctl to enable or disable the feature at runtime
without rebooting. Why we need this? There are 3 use cases.
1) The feature of minimizing overhead of struct page associated with
each HugeTLB is disabled by default without passing
"hugetlb_free_vmemmap=on" to the boot cmdline. When we (ByteDance)
deliver the servers to the users who want to enable this feature, they
have to configure the grub (change boot cmdline) and reboot the
servers, whereas rebooting usually takes a long time (we have thousands
of servers). It's a very bad experience for the users. So we need a
approach to enable this feature after rebooting. This is a use case in
our practical environment.
2) Some use cases are that HugeTLB pages are allocated 'on the fly'
instead of being pulled from the HugeTLB pool, those workloads would be
affected with this feature enabled. Those workloads could be
identified by the characteristics of they never explicitly allocating
huge pages with 'nr_hugepages' but only set 'nr_overcommit_hugepages'
and then let the pages be allocated from the buddy allocator at fault
time. We can confirm it is a real use case from the commit
099730d674. For those workloads, the page fault time could be ~2x
slower than before. We suspect those users want to disable this
feature if the system has enabled this before and they don't think the
memory savings benefit is enough to make up for the performance drop.
3) If the workload which wants vmemmap pages to be optimized and the
workload which wants to set 'nr_overcommit_hugepages' and does not want
the extera overhead at fault time when the overcommitted pages be
allocated from the buddy allocator are deployed in the same server.
The user could enable this feature and set 'nr_hugepages' and
'nr_overcommit_hugepages', then disable the feature. In this case, the
overcommited HugeTLB pages will not encounter the extra overhead at
fault time.
Link: https://lkml.kernel.org/r/20220512041142.39501-5-songmuchun@bytedance.com
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Luis Chamberlain <mcgrof@kernel.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Iurii Zaikin <yzaikin@google.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: David Hildenbrand <david@redhat.com>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Xiongchun Duan <duanxiongchun@bytedance.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Optimizing HugeTLB vmemmap pages is not compatible with allocating memmap
on hot added memory. If "hugetlb_free_vmemmap=on" and
memory_hotplug.memmap_on_memory" are both passed on the kernel command
line, optimizing hugetlb pages takes precedence. However, the global
variable memmap_on_memory will still be set to 1, even though we will not
try to allocate memmap on hot added memory.
Also introduce mhp_memmap_on_memory() helper to move the definition of
"memmap_on_memory" to the scope of CONFIG_MHP_MEMMAP_ON_MEMORY. In the
next patch, mhp_memmap_on_memory() will also be exported to be used in
hugetlb_vmemmap.c.
Link: https://lkml.kernel.org/r/20220512041142.39501-3-songmuchun@bytedance.com
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Acked-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Iurii Zaikin <yzaikin@google.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Kees Cook <keescook@chromium.org>
Cc: Luis Chamberlain <mcgrof@kernel.org>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Xiongchun Duan <duanxiongchun@bytedance.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Patch series "add hugetlb_optimize_vmemmap sysctl", v11.
This series aims to add hugetlb_optimize_vmemmap sysctl to enable or
disable the feature of optimizing vmemmap pages associated with HugeTLB
pages.
This patch (of 4):
If the size of "struct page" is not the power of two but with the feature
of minimizing overhead of struct page associated with each HugeTLB is
enabled, then the vmemmap pages of HugeTLB will be corrupted after
remapping (panic is about to happen in theory). But this only exists when
!CONFIG_MEMCG && !CONFIG_SLUB on x86_64. However, it is not a
conventional configuration nowadays. So it is not a real word issue, just
the result of a code review.
But we cannot prevent anyone from configuring that combined configure.
This hugetlb_optimize_vmemmap should be disable in this case to fix this
issue.
Link: https://lkml.kernel.org/r/20220512041142.39501-1-songmuchun@bytedance.com
Link: https://lkml.kernel.org/r/20220512041142.39501-2-songmuchun@bytedance.com
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Iurii Zaikin <yzaikin@google.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Kees Cook <keescook@chromium.org>
Cc: Luis Chamberlain <mcgrof@kernel.org>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Xiongchun Duan <duanxiongchun@bytedance.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Patch series "Extend and reorganize Highmem's documentation", v4.
This series has the purpose to extend and reorganize Highmem's
documentation.
This is a work in progress because some information should still be moved
from highmem.rst to highmem.h and highmem-internal.h. Specifically I'm
talking about moving the "how to" information to the relevant headers, as
it as been suggested by Ira Weiny (Intel).
Also, this is a work in progress because some kdocs in highmem.h and
highmem-internal.h should be improved.
This patch (of 4):
`scripts/kernel-doc -v -none include/linux/highmem*` reports the following
warnings:
include/linux/highmem.h:160: warning: expecting prototype for kunmap_atomic(). Prototype was for nr_free_highpages() instead
include/linux/highmem.h:204: warning: No description found for return value of 'alloc_zeroed_user_highpage_movable'
include/linux/highmem-internal.h:256: warning: Function parameter or member '__addr' not described in 'kunmap_atomic'
include/linux/highmem-internal.h:256: warning: Excess function parameter 'addr' description in 'kunmap_atomic'
Fix these warnings by (1) moving the kernel-doc comments from highmem.h to
highmem-internal.h (which is the file were the kunmap_atomic() macro is
actually defined), (2) extending and merging it with the comment which was
already in highmem-internal.h, and (3) using correct parameter names (4)
correcting a few technical inaccuracies in comments, and (5) adding a
deprecation notice in kunmap_atomic() for consistency with kmap_atomic().
Link: https://lkml.kernel.org/r/20220428212455.892-1-fmdefrancesco@gmail.com
Link: https://lkml.kernel.org/r/20220428212455.892-2-fmdefrancesco@gmail.com
Signed-off-by: Fabio M. De Francesco <fmdefrancesco@gmail.com>
Reviewed-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Mike Rapoport <rppt@linux.ibm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: Peter Collingbourne <pcc@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Jonathan Corbet <corbet@lwn.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
