mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2025-01-01 10:45:49 +00:00
5ebdc6be16
200 Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
Kairui Song
|
da0c02516c |
mm/list_lru: simplify the list_lru walk callback function
Now isolation no longer takes the list_lru global node lock, only use the per-cgroup lock instead. And this lock is inside the list_lru_one being walked, no longer needed to pass the lock explicitly. Link: https://lkml.kernel.org/r/20241104175257.60853-7-ryncsn@gmail.com Signed-off-by: Kairui Song <kasong@tencent.com> Cc: Chengming Zhou <zhouchengming@bytedance.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Muchun Song <muchun.song@linux.dev> Cc: Qi Zheng <zhengqi.arch@bytedance.com> Cc: Roman Gushchin <roman.gushchin@linux.dev> Cc: Shakeel Butt <shakeel.butt@linux.dev> Cc: Waiman Long <longman@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> |
||
|
Kairui Song
|
fb56fdf8b9 |
mm/list_lru: split the lock to per-cgroup scope
Currently, every list_lru has a per-node lock that protects adding,
deletion, isolation, and reparenting of all list_lru_one instances
belonging to this list_lru on this node. This lock contention is heavy
when multiple cgroups modify the same list_lru.
This lock can be split into per-cgroup scope to reduce contention.
To achieve this, we need a stable list_lru_one for every cgroup. This
commit adds a lock to each list_lru_one and introduced a helper function
lock_list_lru_of_memcg, making it possible to pin the list_lru of a memcg.
Then reworked the reparenting process.
Reparenting will switch the list_lru_one instances one by one. By locking
each instance and marking it dead using the nr_items counter, reparenting
ensures that all items in the corresponding cgroup (on-list or not,
because items have a stable cgroup, see below) will see the list_lru_one
switch synchronously.
Objcg reparent is also moved after list_lru reparent so items will have a
stable mem cgroup until all list_lru_one instances are drained.
The only caller that doesn't work the *_obj interfaces are direct calls to
list_lru_{add,del}. But it's only used by zswap and that's also based on
objcg, so it's fine.
This also changes the bahaviour of the isolation function when LRU_RETRY
or LRU_REMOVED_RETRY is returned, because now releasing the lock could
unblock reparenting and free the list_lru_one, isolation function will
have to return withoug re-lock the lru.
prepare() {
mkdir /tmp/test-fs
modprobe brd rd_nr=1 rd_size=33554432
mkfs.xfs -f /dev/ram0
mount -t xfs /dev/ram0 /tmp/test-fs
for i in $(seq 1 512); do
mkdir "/tmp/test-fs/$i"
for j in $(seq 1 10240); do
echo TEST-CONTENT > "/tmp/test-fs/$i/$j"
done &
done; wait
}
do_test() {
read_worker() {
sleep 1
tar -cv "$1" &>/dev/null
}
read_in_all() {
cd "/tmp/test-fs" && ls
for i in $(seq 1 512); do
(exec sh -c 'echo "$PPID"') > "/sys/fs/cgroup/benchmark/$i/cgroup.procs"
read_worker "$i" &
done; wait
}
for i in $(seq 1 512); do
mkdir -p "/sys/fs/cgroup/benchmark/$i"
done
echo +memory > /sys/fs/cgroup/benchmark/cgroup.subtree_control
echo 512M > /sys/fs/cgroup/benchmark/memory.max
echo 3 > /proc/sys/vm/drop_caches
time read_in_all
}
Above script simulates compression of small files in multiple cgroups
with memory pressure. Run prepare() then do_test for 6 times:
Before:
real 0m7.762s user 0m11.340s sys 3m11.224s
real 0m8.123s user 0m11.548s sys 3m2.549s
real 0m7.736s user 0m11.515s sys 3m11.171s
real 0m8.539s user 0m11.508s sys 3m7.618s
real 0m7.928s user 0m11.349s sys 3m13.063s
real 0m8.105s user 0m11.128s sys 3m14.313s
After this commit (about ~15% faster):
real 0m6.953s user 0m11.327s sys 2m42.912s
real 0m7.453s user 0m11.343s sys 2m51.942s
real 0m6.916s user 0m11.269s sys 2m43.957s
real 0m6.894s user 0m11.528s sys 2m45.346s
real 0m6.911s user 0m11.095s sys 2m43.168s
real 0m6.773s user 0m11.518s sys 2m40.774s
Link: https://lkml.kernel.org/r/20241104175257.60853-6-ryncsn@gmail.com
Signed-off-by: Kairui Song <kasong@tencent.com>
Cc: Chengming Zhou <zhouchengming@bytedance.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Shakeel Butt <shakeel.butt@linux.dev>
Cc: Waiman Long <longman@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
|
||
|
Kairui Song
|
28e98022b3 |
mm/list_lru: simplify reparenting and initial allocation
Currently, there is a lot of code for detecting reparent racing using
kmemcg_id as the synchronization flag. And an intermediate table is
required to record and compare the kmemcg_id.
We can simplify this by just checking the cgroup css status, skip if
cgroup is being offlined. On the reparenting side, ensure no more
allocation is on going and no further allocation will occur by using the
XArray lock as barrier.
Combined with a O(n^2) top-down walk for the allocation, we get rid of the
intermediate table allocation completely. Despite being O(n^2), it should
be actually faster because it's not practical to have a very deep cgroup
level, and in most cases the parent cgroup should have been allocated
already.
This also avoided changing kmemcg_id before reparenting, making cgroups
have a stable index for list_lru_memcg. After this change it's possible
that a dying cgroup will see a NULL value in XArray corresponding to the
kmemcg_id, because the kmemcg_id will point to an empty slot. In such
case, just fallback to use its parent.
As a result the code is simpler, following test also showed a very slight
performance gain (12 test runs):
prepare() {
mkdir /tmp/test-fs
modprobe brd rd_nr=1 rd_size=16777216
mkfs.xfs -f /dev/ram0
mount -t xfs /dev/ram0 /tmp/test-fs
for i in $(seq 10000); do
seq 8000 > "/tmp/test-fs/$i"
done
mkdir -p /sys/fs/cgroup/system.slice/bench/test/1
echo +memory > /sys/fs/cgroup/system.slice/bench/cgroup.subtree_control
echo +memory > /sys/fs/cgroup/system.slice/bench/test/cgroup.subtree_control
echo +memory > /sys/fs/cgroup/system.slice/bench/test/1/cgroup.subtree_control
echo 768M > /sys/fs/cgroup/system.slice/bench/memory.max
}
do_test() {
read_worker() {
mkdir -p "/sys/fs/cgroup/system.slice/bench/test/1/$1"
echo $BASHPID > "/sys/fs/cgroup/system.slice/bench/test/1/$1/cgroup.procs"
read -r __TMP < "/tmp/test-fs/$1";
}
read_in_all() {
for i in $(seq 10000); do
read_worker "$i" &
done; wait
}
echo 3 > /proc/sys/vm/drop_caches
time read_in_all
for i in $(seq 1 10000); do
rmdir "/sys/fs/cgroup/system.slice/bench/test/1/$i" &>/dev/null
done
}
Before:
real 0m3.498s user 0m11.037s sys 0m35.872s
real 1m33.860s user 0m11.593s sys 3m1.169s
real 1m31.883s user 0m11.265s sys 2m59.198s
real 1m32.394s user 0m11.294s sys 3m1.616s
real 1m31.017s user 0m11.379s sys 3m1.349s
real 1m31.931s user 0m11.295s sys 2m59.863s
real 1m32.758s user 0m11.254s sys 2m59.538s
real 1m35.198s user 0m11.145s sys 3m1.123s
real 1m30.531s user 0m11.393s sys 2m58.089s
real 1m31.142s user 0m11.333s sys 3m0.549s
After:
real 0m3.489s user 0m10.943s sys 0m36.036s
real 1m10.893s user 0m11.495s sys 2m38.545s
real 1m29.129s user 0m11.382s sys 3m1.601s
real 1m29.944s user 0m11.494s sys 3m1.575s
real 1m31.208s user 0m11.451s sys 2m59.693s
real 1m25.944s user 0m11.327s sys 2m56.394s
real 1m28.599s user 0m11.312s sys 3m0.162s
real 1m26.746s user 0m11.538s sys 2m55.462s
real 1m30.668s user 0m11.475s sys 3m2.075s
real 1m29.258s user 0m11.292s sys 3m0.780s
Which is slightly faster in real time.
Link: https://lkml.kernel.org/r/20241104175257.60853-5-ryncsn@gmail.com
Signed-off-by: Kairui Song <kasong@tencent.com>
Cc: Chengming Zhou <zhouchengming@bytedance.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Shakeel Butt <shakeel.butt@linux.dev>
Cc: Waiman Long <longman@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
|
||
|
Kanchana P Sridhar
|
ed882add6d |
mm: zswap: zswap_store_page() will initialize entry after adding to xarray.
This incorporates Yosry's suggestions in [1] for further simplifying zswap_store_page(). If the page is successfully compressed and added to the xarray, we get the pool/objcg refs, and initialize all the entry's members. Only after this, we add it to the zswap LRU. In the time between the entry's addition to the xarray and it's member initialization, we are protected against concurrent stores/loads/swapoff through the folio lock, and are protected against writeback because the entry is not on the LRU yet. This way, we don't have to drop the pool/objcg refs, now that the entry initialization is centralized to the successful page store code path. zswap_compress() is modified to take a zswap_pool parameter in keeping with this simplification (as against obtaining this from entry->pool). [1]: https://lore.kernel.org/all/CAJD7tkZh6ufHQef5HjXf_F5b5LC1EATexgseD=4WvrO+a6Ni6w@mail.gmail.com/ Link: https://lkml.kernel.org/r/20241002173329.213722-1-kanchana.p.sridhar@intel.com Signed-off-by: Kanchana P Sridhar <kanchana.p.sridhar@intel.com> Cc: Chengming Zhou <chengming.zhou@linux.dev> Cc: Huang Ying <ying.huang@intel.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Nhat Pham <nphamcs@gmail.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Wajdi Feghali <wajdi.k.feghali@intel.com> Cc: Yosry Ahmed <yosryahmed@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> |
||
|
Kanchana P Sridhar
|
b7c0ccdfba |
mm: zswap: support large folios in zswap_store()
This series enables zswap_store() to accept and store large folios. The
most significant contribution in this series is from the earlier RFC
submitted by Ryan Roberts [1]. Ryan's original RFC has been migrated to
mm-unstable as of 9-30-2024 in patch 6 of this series, and adapted based
on code review comments received for the current patch-series.
[1]: [RFC PATCH v1] mm: zswap: Store large folios without splitting
https://lore.kernel.org/linux-mm/20231019110543.3284654-1-ryan.roberts@arm.com/T/#u
The first few patches do the prep work for supporting large folios in
zswap_store. Patch 6 provides the main functionality to swap-out large
folios in zswap. Patch 7 adds sysfs per-order hugepages "zswpout"
counters that get incremented upon successful zswap_store of large folios,
and also updates the documentation for this:
/sys/kernel/mm/transparent_hugepage/hugepages-*kB/stats/zswpout
This series is a pre-requisite for zswap compress batching of large folio
swap-out and decompress batching of swap-ins based on swapin_readahead(),
using Intel IAA hardware acceleration, which we would like to submit in
subsequent patch-series, with performance improvement data.
Thanks to Ying Huang for pre-posting review feedback and suggestions!
Thanks also to Nhat, Yosry, Johannes, Barry, Chengming, Usama, Ying and
Matthew for their helpful feedback, code/data reviews and suggestions!
I would like to thank Ryan Roberts for his original RFC [1].
System setup for testing:
=========================
Testing of this series was done with mm-unstable as of 9-27-2024, commit
de2fbaa6d9c3576ec7133ed02a370ec9376bf000 (without this patch-series) and
mm-unstable 9-30-2024 commit c121617e3606be6575cdacfdb63cc8d67b46a568
(with this patch-series). Data was gathered on an Intel Sapphire Rapids
server, dual-socket 56 cores per socket, 4 IAA devices per socket, 503 GiB
RAM and 525G SSD disk partition swap. Core frequency was fixed at
2500MHz.
The vm-scalability "usemem" test was run in a cgroup whose memory.high was
fixed at 150G. The is no swap limit set for the cgroup. 30 usemem
processes were run, each allocating and writing 10G of memory, and
sleeping for 10 sec before exiting:
usemem --init-time -w -O -s 10 -n 30 10g
Other kernel configuration parameters:
zswap compressors : zstd, deflate-iaa
zswap allocator : zsmalloc
vm.page-cluster : 2
In the experiments where "deflate-iaa" is used as the zswap compressor,
IAA "compression verification" is enabled by default (cat
/sys/bus/dsa/drivers/crypto/verify_compress). Hence each IAA compression
will be decompressed internally by the "iaa_crypto" driver, the crc-s
returned by the hardware will be compared and errors reported in case of
mismatches. Thus "deflate-iaa" helps ensure better data integrity as
compared to the software compressors, and the experimental data listed
below is with verify_compress set to "1".
Metrics reporting methodology:
==============================
Total and average throughput are derived from the individual 30 processes'
throughputs reported by usemem. elapsed/sys times are measured with perf.
All percentage changes are "new" vs. "old"; hence a positive value
denotes an increase in the metric, whether it is throughput or latency,
and a negative value denotes a reduction in the metric. Positive
throughput change percentages and negative latency change percentages
denote improvements.
The vm stats and sysfs hugepages stats included with the performance data
provide details on the swapout activity to zswap/swap device.
Testing labels used in data summaries:
======================================
The data refers to these test configurations and the before/after
comparisons that they do:
before-case1:
-------------
mm-unstable 9-27-2024, CONFIG_THP_SWAP=N (compares zswap 4K vs. zswap 64K)
In this scenario, CONFIG_THP_SWAP=N results in 64K/2M folios to be split
into 4K folios that get processed by zswap.
before-case2:
-------------
mm-unstable 9-27-2024, CONFIG_THP_SWAP=Y (compares SSD swap large folios vs. zswap large folios)
In this scenario, CONFIG_THP_SWAP=Y results in zswap rejecting large
folios, which will then be stored by the SSD swap device.
after:
------
v10 of this patch-series, CONFIG_THP_SWAP=Y
The "after" is CONFIG_THP_SWAP=Y and v10 of this patch-series, that results
in 64K/2M folios to not be split, and to be processed by zswap_store.
Regression Testing:
===================
I ran vm-scalability usemem without large folios, i.e., only 4K folios with
mm-unstable and this patch-series. The main goal was to make sure that
there is no functional or performance regression wrt the earlier zswap
behavior for 4K folios, now that 4K folios will be processed by the new
zswap_store() code.
The data indicates there is no significant regression.
-------------------------------------------------------------------------------
4K folios:
==========
zswap compressor zstd zstd zstd zstd v10
before-case1 before-case2 after vs. vs.
case1 case2
-------------------------------------------------------------------------------
Total throughput (KB/s) 4,793,363 4,880,978 4,853,074 1% -1%
Average throughput (KB/s) 159,778 162,699 161,769 1% -1%
elapsed time (sec) 130.14 123.17 126.29 -3% 3%
sys time (sec) 3,135.53 2,985.64 3,083.18 -2% 3%
memcg_high 446,826 444,626 452,930
memcg_swap_fail 0 0 0
zswpout 48,932,107 48,931,971 48,931,820
zswpin 383 386 397
pswpout 0 0 0
pswpin 0 0 0
thp_swpout 0 0 0
thp_swpout_fallback 0 0 0
64kB-mthp_swpout_fallback 0 0 0
pgmajfault 3,063 3,077 3,479
swap_ra 93 94 96
swap_ra_hit 47 47 50
ZSWPOUT-64kB n/a n/a 0
SWPOUT-64kB 0 0 0
-------------------------------------------------------------------------------
Performance Testing:
====================
We list the data for 64K folios with before/after data per-compressor,
followed by the same for 2M pmd-mappable folios.
-------------------------------------------------------------------------------
64K folios: zstd:
=================
zswap compressor zstd zstd zstd zstd v10
before-case1 before-case2 after vs. vs.
case1 case2
-------------------------------------------------------------------------------
Total throughput (KB/s) 5,222,213 1,076,611 6,159,776 18% 472%
Average throughput (KB/s) 174,073 35,887 205,325 18% 472%
elapsed time (sec) 120.50 347.16 108.33 -10% -69%
sys time (sec) 2,930.33 248.16 2,549.65 -13% 927%
memcg_high 416,773 552,200 465,874
memcg_swap_fail 3,192,906 1,293 1,012
zswpout 48,931,583 20,903 48,931,218
zswpin 384 363 410
pswpout 0 40,778,448 0
pswpin 0 16 0
thp_swpout 0 0 0
thp_swpout_fallback 0 0 0
64kB-mthp_swpout_fallback 3,192,906 1,293 1,012
pgmajfault 3,452 3,072 3,061
swap_ra 90 87 107
swap_ra_hit 42 43 57
ZSWPOUT-64kB n/a n/a 3,057,173
SWPOUT-64kB 0 2,548,653 0
-------------------------------------------------------------------------------
-------------------------------------------------------------------------------
64K folios: deflate-iaa:
========================
zswap compressor deflate-iaa deflate-iaa deflate-iaa deflate-iaa v10
before-case1 before-case2 after vs. vs.
case1 case2
-------------------------------------------------------------------------------
Total throughput (KB/s) 5,652,608 1,089,180 7,189,778 27% 560%
Average throughput (KB/s) 188,420 36,306 239,659 27% 560%
elapsed time (sec) 102.90 343.35 87.05 -15% -75%
sys time (sec) 2,246.86 213.53 1,864.16 -17% 773%
memcg_high 576,104 502,907 642,083
memcg_swap_fail 4,016,117 1,407 1,478
zswpout 61,163,423 22,444 57,798,716
zswpin 401 368 454
pswpout 0 40,862,080 0
pswpin 0 20 0
thp_swpout 0 0 0
thp_swpout_fallback 0 0 0
64kB-mthp_swpout_fallback 4,016,117 1,407 1,478
pgmajfault 3,063 3,153 3,122
swap_ra 96 93 156
swap_ra_hit 46 45 83
ZSWPOUT-64kB n/a n/a 3,611,032
SWPOUT-64kB 0 2,553,880 0
-------------------------------------------------------------------------------
-------------------------------------------------------------------------------
2M folios: zstd:
================
zswap compressor zstd zstd zstd zstd v10
before-case1 before-case2 after vs. vs.
case1 case2
-------------------------------------------------------------------------------
Total throughput (KB/s) 5,895,500 1,109,694 6,484,224 10% 484%
Average throughput (KB/s) 196,516 36,989 216,140 10% 484%
elapsed time (sec) 108.77 334.28 106.33 -2% -68%
sys time (sec) 2,657.14 94.88 2,376.13 -11% 2404%
memcg_high 64,200 66,316 56,898
memcg_swap_fail 101,182 70 27
zswpout 48,931,499 36,507 48,890,640
zswpin 380 379 377
pswpout 0 40,166,400 0
pswpin 0 0 0
thp_swpout 0 78,450 0
thp_swpout_fallback 101,182 70 27
2MB-mthp_swpout_fallback 0 0 27
pgmajfault 3,067 3,417 3,311
swap_ra 91 90 854
swap_ra_hit 45 45 810
ZSWPOUT-2MB n/a n/a 95,459
SWPOUT-2MB 0 78,450 0
-------------------------------------------------------------------------------
-------------------------------------------------------------------------------
2M folios: deflate-iaa:
=======================
zswap compressor deflate-iaa deflate-iaa deflate-iaa deflate-iaa v10
before-case1 before-case2 after vs. vs.
case1 case2
-------------------------------------------------------------------------------
Total throughput (KB/s) 6,286,587 1,126,785 7,073,464 13% 528%
Average throughput (KB/s) 209,552 37,559 235,782 13% 528%
elapsed time (sec) 96.19 333.03 85.79 -11% -74%
sys time (sec) 2,141.44 99.96 1,826.67 -15% 1727%
memcg_high 99,253 64,666 79,718
memcg_swap_fail 129,074 53 165
zswpout 61,312,794 28,321 56,045,120
zswpin 383 406 403
pswpout 0 40,048,128 0
pswpin 0 0 0
thp_swpout 0 78,219 0
thp_swpout_fallback 129,074 53 165
2MB-mthp_swpout_fallback 0 0 165
pgmajfault 3,430 3,077 31,468
swap_ra 91 103 84,373
swap_ra_hit 47 46 84,317
ZSWPOUT-2MB n/a n/a 109,229
SWPOUT-2MB 0 78,219 0
-------------------------------------------------------------------------------
And finally, this is a comparison of deflate-iaa vs. zstd with v10 of this
patch-series:
---------------------------------------------
zswap_store large folios v10
Impr w/ deflate-iaa vs. zstd
64K folios 2M folios
---------------------------------------------
Throughput (KB/s) 17% 9%
elapsed time (sec) -20% -19%
sys time (sec) -27% -23%
---------------------------------------------
Conclusions based on the performance results:
=============================================
v10 wrt before-case1:
---------------------
We see significant improvements in throughput, elapsed and sys time for
zstd and deflate-iaa, when comparing before-case1 (THP_SWAP=N) vs. after
(THP_SWAP=Y) with zswap_store large folios.
v10 wrt before-case2:
---------------------
We see even more significant improvements in throughput and elapsed time
for zstd and deflate-iaa, when comparing before-case2 (large-folio-SSD)
vs. after (large-folio-zswap). The sys time increases with
large-folio-zswap as expected, due to the CPU compression time
vs. asynchronous disk write times, as pointed out by Ying and Yosry.
In before-case2, when zswap does not store large folios, only allocations
and cgroup charging due to 4K folio zswap stores count towards the cgroup
memory limit. However, in the after scenario, with the introduction of
zswap_store() of large folios, there is an added component of the zswap
compressed pool usage from large folio stores from potentially all 30
processes, that gets counted towards the memory limit. As a result, we see
higher swapout activity in the "after" data.
Summary:
========
The v10 data presented above shows that zswap_store of large folios
demonstrates good throughput/performance improvements compared to
conventional SSD swap of large folios with a sufficiently large 525G SSD
swap device. Hence, it seems reasonable for zswap_store to support large
folios, so that further performance improvements can be implemented.
In the experimental setup used in this patchset, we have enabled IAA
compress verification to ensure additional hardware data integrity CRC
checks not currently done by the software compressors. We see good
throughput/latency improvements with deflate-iaa vs. zstd with zswap_store
of large folios.
Some of the ideas for further reducing latency that have shown promise in
our experiments, are:
1) IAA compress/decompress batching.
2) Distributing compress jobs across all IAA devices on the socket.
The tests run for this patchset are using only 1 IAA device per core, that
avails of 2 compress engines on the device. In our experiments with IAA
batching, we distribute compress jobs from all cores to the 8 compress
engines available per socket. We further compress the pages in each folio
in parallel in the accelerator. As a result, we improve compress latency
and reclaim throughput.
In decompress batching, we use swapin_readahead to generate a prefetch
batch of 4K folios that we decompress in parallel in IAA.
------------------------------------------------------------------------------
IAA compress/decompress batching
Further improvements wrt v10 zswap_store Sequential
subpage store using "deflate-iaa":
"deflate-iaa" Batching "deflate-iaa-canned" [2] Batching
Additional Impr Additional Impr
64K folios 2M folios 64K folios 2M folios
------------------------------------------------------------------------------
Throughput (KB/s) 19% 43% 26% 55%
elapsed time (sec) -5% -14% -10% -21%
sys time (sec) 4% -7% -4% -18%
------------------------------------------------------------------------------
With zswap IAA compress/decompress batching, we are able to demonstrate
significant performance improvements and memory savings in server
scalability experiments in highly contended system scenarios under
significant memory pressure; as compared to software compressors. We hope
to submit this work in subsequent patch series. The current patch-series
is a prequisite for these future submissions.
This patch (of 7):
zswap_store() will store large folios by compressing them page by page.
This patch provides a sequential implementation of storing a large folio
in zswap_store() by iterating through each page in the folio to compress
and store it in the zswap zpool.
zswap_store() calls the newly added zswap_store_page() function for each
page in the folio. zswap_store_page() handles compressing and storing
each page.
We check the global and per-cgroup limits once at the beginning of
zswap_store(), and only check that the limit is not reached yet. This is
racy and inaccurate, but it should be sufficient for now. We also obtain
initial references to the relevant objcg and pool to guarantee that
subsequent references can be acquired by zswap_store_page(). A new
function zswap_pool_get() is added to facilitate this.
If these one-time checks pass, we compress the pages of the folio, while
maintaining a running count of compressed bytes for all the folio's pages.
If all pages are successfully compressed and stored, we do the cgroup
zswap charging with the total compressed bytes, and batch update the
zswap_stored_pages atomic/zswpout event stats with folio_nr_pages() once,
before returning from zswap_store().
If an error is encountered during the store of any page in the folio, all
pages in that folio currently stored in zswap will be invalidated. Thus,
a folio is either entirely stored in zswap, or entirely not stored in
zswap.
The most important value provided by this patch is it enables swapping out
large folios to zswap without splitting them. Furthermore, it batches
some operations while doing so (cgroup charging, stats updates).
This patch also forms the basis for building compress batching of pages in
a large folio in zswap_store() by compressing up to say, 8 pages of the
folio in parallel in hardware using the Intel In-Memory Analytics
Accelerator (Intel IAA).
This change reuses and adapts the functionality in Ryan Roberts' RFC
patch [1]:
"[RFC,v1] mm: zswap: Store large folios without splitting"
[1] https://lore.kernel.org/linux-mm/20231019110543.3284654-1-ryan.roberts@arm.com/T/#u
Link: https://lkml.kernel.org/r/20241001053222.6944-1-kanchana.p.sridhar@intel.com
Link: https://lkml.kernel.org/r/20241001053222.6944-7-kanchana.p.sridhar@intel.com
Signed-off-by: Kanchana P Sridhar <kanchana.p.sridhar@intel.com>
Originally-by: Ryan Roberts <ryan.roberts@arm.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Yosry Ahmed <yosryahmed@google.com>
Reviewed-by: Nhat Pham <nphamcs@gmail.com>
Cc: Chengming Zhou <chengming.zhou@linux.dev>
Cc: "Huang, Ying" <ying.huang@intel.com>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: Shakeel Butt <shakeel.butt@linux.dev>
Cc: Usama Arif <usamaarif642@gmail.com>
Cc: Wajdi Feghali <wajdi.k.feghali@intel.com>
Cc: "Zou, Nanhai" <nanhai.zou@intel.com>
Cc: Barry Song <21cnbao@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
|
||
|
Kanchana P Sridhar
|
6e1fa555ec |
mm: zswap: modify zswap_stored_pages to be atomic_long_t
For zswap_store() to support large folios, we need to be able to do a batch update of zswap_stored_pages upon successful store of all pages in the folio. For this, we need to add folio_nr_pages(), which returns a long, to zswap_stored_pages. Link: https://lkml.kernel.org/r/20241001053222.6944-6-kanchana.p.sridhar@intel.com Signed-off-by: Kanchana P Sridhar <kanchana.p.sridhar@intel.com> Acked-by: Yosry Ahmed <yosryahmed@google.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Nhat Pham <nphamcs@gmail.com> Cc: Chengming Zhou <chengming.zhou@linux.dev> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Shakeel Butt <shakeel.butt@linux.dev> Cc: Usama Arif <usamaarif642@gmail.com> Cc: Wajdi Feghali <wajdi.k.feghali@intel.com> Cc: "Zou, Nanhai" <nanhai.zou@intel.com> Cc: Barry Song <21cnbao@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> |
||
|
Kanchana P Sridhar
|
0201c054c2 |
mm: zswap: rename zswap_pool_get() to zswap_pool_tryget()
Modify the name of the existing zswap_pool_get() to zswap_pool_tryget() to be representative of the call it makes to percpu_ref_tryget(). A subsequent patch will introduce a new zswap_pool_get() that calls percpu_ref_get(). The intent behind this change is for higher level zswap API such as zswap_store() to call zswap_pool_tryget() to check upfront if the pool's refcount is "0" (which means it could be getting destroyed) and to handle this as an error condition. zswap_store() would proceed only if zswap_pool_tryget() returns success, and any additional pool refcounts that need to be obtained for compressing sub-pages in a large folio could simply call zswap_pool_get(). Link: https://lkml.kernel.org/r/20241001053222.6944-4-kanchana.p.sridhar@intel.com Signed-off-by: Kanchana P Sridhar <kanchana.p.sridhar@intel.com> Acked-by: Yosry Ahmed <yosryahmed@google.com> Reviewed-by: Chengming Zhou <chengming.zhou@linux.dev> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Nhat Pham <nphamcs@gmail.com> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Shakeel Butt <shakeel.butt@linux.dev> Cc: Usama Arif <usamaarif642@gmail.com> Cc: Wajdi Feghali <wajdi.k.feghali@intel.com> Cc: "Zou, Nanhai" <nanhai.zou@intel.com> Cc: Barry Song <21cnbao@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> |
||
|
Kanchana P Sridhar
|
3d0f560a36 |
mm: zswap: modify zswap_compress() to accept a page instead of a folio
For zswap_store() to be able to store a large folio by compressing it one page at a time, zswap_compress() needs to accept a page as input. This will allow us to iterate through each page in the folio in zswap_store(), compress it and store it in the zpool. Link: https://lkml.kernel.org/r/20241001053222.6944-3-kanchana.p.sridhar@intel.com Signed-off-by: Kanchana P Sridhar <kanchana.p.sridhar@intel.com> Reviewed-by: Nhat Pham <nphamcs@gmail.com> Reviewed-by: Chengming Zhou <chengming.zhou@linux.dev> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Yosry Ahmed <yosryahmed@google.com> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Shakeel Butt <shakeel.butt@linux.dev> Cc: Usama Arif <usamaarif642@gmail.com> Cc: Wajdi Feghali <wajdi.k.feghali@intel.com> Cc: "Zou, Nanhai" <nanhai.zou@intel.com> Cc: Barry Song <21cnbao@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> |
||
|
Andrew Morton
|
2ec0859039 |
Merge branch 'mm-hotfixes-stable' into mm-stable
Pick up
|
||
|
Barry Song
|
e7ac4daeed |
mm: count zeromap read and set for swapout and swapin
When the proportion of folios from the zeromap is small, missing their accounting may not significantly impact profiling. However, it's easy to construct a scenario where this becomes an issue—for example, allocating 1 GB of memory, writing zeros from userspace, followed by MADV_PAGEOUT, and then swapping it back in. In this case, the swap-out and swap-in counts seem to vanish into a black hole, potentially causing semantic ambiguity. On the other hand, Usama reported that zero-filled pages can exceed 10% in workloads utilizing zswap, while Hailong noted that some app in Android have more than 6% zero-filled pages. Before commit |
||
|
Kairui Song
|
773ee2cda5 |
mm/zswap: avoid touching XArray for unnecessary invalidation
zswap_invalidation simply calls xa_erase, which acquires the Xarray lock first, then does a look up. This has a higher overhead even if zswap is not used or the tree is empty. So instead, do a very lightweight xa_empty check first, if there is nothing to erase, don't touch the lock or the tree. Using xa_empty rather than zswap_never_enabled is more helpful as it cover both case where zswap wes never used or the particular range doesn't have any zswap entry. And it's safe as the swap slot should be currently pinned by caller with HAS_CACHE. Sequential SWAP in/out tests with zswap disabled showed a minor performance gain, SWAP in of zero page with zswap enabled also showed a performance gain. (swapout is basically unchanged so only test one case): Swapout of 2G zero page using brd as SWAP, zswap disabled (total time, 4 testrun, +0.1%): Before: |
||
|
Kanchana P Sridhar
|
aa5f0fa6af |
mm: zswap: delete comments for "value" member of 'struct zswap_entry'.
Made a minor edit in the comments for 'struct zswap_entry' to delete the description of the 'value' member that was deleted in commit |
||
|
Usama Arif
|
20a5532ffa |
mm: remove code to handle same filled pages
With an earlier commit to handle zero-filled pages in swap directly, and with only 1% of the same-filled pages being non-zero, zswap no longer needs to handle same-filled pages and can just work on compressed pages. Link: https://lkml.kernel.org/r/20240823190545.979059-3-usamaarif642@gmail.com Signed-off-by: Usama Arif <usamaarif642@gmail.com> Reviewed-by: Chengming Zhou <chengming.zhou@linux.dev> Acked-by: Yosry Ahmed <yosryahmed@google.com> Reviewed-by: Nhat Pham <nphamcs@gmail.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Andi Kleen <ak@linux.intel.com> Cc: David Hildenbrand <david@redhat.com> Cc: Hugh Dickins <hughd@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Shakeel Butt <shakeel.butt@linux.dev> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> |
||
|
Nhat Pham
|
e31c38e037 |
zswap: implement a second chance algorithm for dynamic zswap shrinker
Patch series "improving dynamic zswap shrinker protection scheme", v3. When experimenting with the memory-pressure based (i.e "dynamic") zswap shrinker in production, we observed a sharp increase in the number of swapins, which led to performance regression. We were able to trace this regression to the following problems with the shrinker's warm pages protection scheme: 1. The protection decays way too rapidly, and the decaying is coupled with zswap stores, leading to anomalous patterns, in which a small batch of zswap stores effectively erase all the protection in place for the warmer pages in the zswap LRU. This observation has also been corroborated upstream by Takero Funaki (in [1]). 2. We inaccurately track the number of swapped in pages, missing the non-pivot pages that are part of the readahead window, while counting the pages that are found in the zswap pool. To alleviate these two issues, this patch series improve the dynamic zswap shrinker in the following manner: 1. Replace the protection size tracking scheme with a second chance algorithm. This new scheme removes the need for haphazard stats decaying, and automatically adjusts the pace of pages aging with memory pressure, and writeback rate with pool activities: slowing down when the pool is dominated with zswpouts, and speeding up when the pool is dominated with stale entries. 2. Fix the tracking of the number of swapins to take into account non-pivot pages in the readahead window. With these two changes in place, in a kernel-building benchmark without any cold data added, the number of swapins is reduced by 64.12%. This translate to a 10.32% reduction in build time. We also observe a 3% reduction in kernel CPU time. In another benchmark, with cold data added (to gauge the new algorithm's ability to offload cold data), the new second chance scheme outperforms the old protection scheme by around 0.7%, and actually written back around 21% more pages to backing swap device. So the new scheme is just as good, if not even better than the old scheme on this front as well. [1]: https://lore.kernel.org/linux-mm/CAPpodddcGsK=0Xczfuk8usgZ47xeyf4ZjiofdT+ujiyz6V2pFQ@mail.gmail.com/ This patch (of 2): Current zswap shrinker's heuristics to prevent overshrinking is brittle and inaccurate, specifically in the way we decay the protection size (i.e making pages in the zswap LRU eligible for reclaim). We currently decay protection aggressively in zswap_lru_add() calls. This leads to the following unfortunate effect: when a new batch of pages enter zswap, the protection size rapidly decays to below 25% of the zswap LRU size, which is way too low. We have observed this effect in production, when experimenting with the zswap shrinker: the rate of shrinking shoots up massively right after a new batch of zswap stores. This is somewhat the opposite of what we want originally - when new pages enter zswap, we want to protect both these new pages AND the pages that are already protected in the zswap LRU. Replace existing heuristics with a second chance algorithm 1. When a new zswap entry is stored in the zswap pool, its referenced bit is set. 2. When the zswap shrinker encounters a zswap entry with the referenced bit set, give it a second chance - only flips the referenced bit and rotate it in the LRU. 3. If the shrinker encounters the entry again, this time with its referenced bit unset, then it can reclaim the entry. In this manner, the aging of the pages in the zswap LRUs are decoupled from zswap stores, and picks up the pace with increasing memory pressure (which is what we want). The second chance scheme allows us to modulate the writeback rate based on recent pool activities. Entries that recently entered the pool will be protected, so if the pool is dominated by such entries the writeback rate will reduce proportionally, protecting the workload's workingset.On the other hand, stale entries will be written back quickly, which increases the effective writeback rate. The referenced bit is added at the hole after the `length` field of struct zswap_entry, so there is no extra space overhead for this algorithm. We will still maintain the count of swapins, which is consumed and subtracted from the lru size in zswap_shrinker_count(), to further penalize past overshrinking that led to disk swapins. The idea is that had we considered this many more pages in the LRU active/protected, they would not have been written back and we would not have had to swapped them in. To test this new heuristics, I built the kernel under a cgroup with memory.max set to 2G, on a host with 36 cores: With the old shrinker: real: 263.89s user: 4318.11s sys: 673.29s swapins: 227300.5 With the second chance algorithm: real: 244.85s user: 4327.22s sys: 664.39s swapins: 94663 (average over 5 runs) We observe an 1.3% reduction in kernel CPU usage, and around 7.2% reduction in real time. Note that the number of swapped in pages dropped by 58%. [nphamcs@gmail.com: fix a small mistake in the referenced bit documentation] Link: https://lkml.kernel.org/r/20240806003403.3142387-1-nphamcs@gmail.com Link: https://lkml.kernel.org/r/20240805232243.2896283-1-nphamcs@gmail.com Link: https://lkml.kernel.org/r/20240805232243.2896283-2-nphamcs@gmail.com Signed-off-by: Nhat Pham <nphamcs@gmail.com> Suggested-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Yosry Ahmed <yosryahmed@google.com> Cc: Chengming Zhou <chengming.zhou@linux.dev> Cc: Shakeel Butt <shakeel.butt@linux.dev> Cc: Takero Funaki <flintglass@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> |
||
|
Takero Funaki
|
81920438a6 |
mm: zswap: fix global shrinker error handling logic
This patch fixes the zswap global shrinker, which did not shrink the zpool
as expected.
The issue addressed is that shrink_worker() did not distinguish between
unexpected errors and expected errors, such as failed writeback from an
empty memcg. The shrinker would stop shrinking after iterating through
the memcg tree 16 times, even if there was only one empty memcg.
With this patch, the shrinker no longer considers encountering an empty
memcg, encountering a memcg with writeback disabled, or reaching the end
of a memcg tree walk as a failure, as long as there are memcgs that are
candidates for writeback. Systems with one or more empty memcgs will now
observe significantly higher zswap writeback activity after the zswap pool
limit is hit.
To avoid an infinite loop when there are no writeback candidates, this
patch tracks writeback attempts during memcg tree walks and limits reties
if no writeback candidates are found.
To handle the empty memcg case, the helper function shrink_memcg() is
modified to check if the memcg is empty and then return -ENOENT.
Link: https://lkml.kernel.org/r/20240731004918.33182-3-flintglass@gmail.com
Fixes:
|
||
|
Takero Funaki
|
c5519e0a9b |
mm: zswap: fix global shrinker memcg iteration
Patch series "mm: zswap: fixes for global shrinker", v5.
This series addresses issues in the zswap global shrinker that could not
shrink stored pages. With this series, the shrinker continues to shrink
pages until it reaches the accept threshold more reliably, gives much
higher writeback when the zswap pool limit is hit.
This patch (of 2):
This patch fixes an issue where the zswap global shrinker stopped
iterating through the memcg tree.
The problem was that shrink_worker() would restart iterating memcg tree
from the tree root, considering an offline memcg as a failure, and abort
shrinking after encountering the same offline memcg 16 times even if there
is only one offline memcg. After this change, an offline memcg in the
tree is no longer considered a failure. This allows the shrinker to
continue shrinking the other online memcgs regardless of whether an
offline memcg exists, gives higher zswap writeback activity.
To avoid holding refcount of offline memcg encountered during the memcg
tree walking, shrink_worker() must continue iterating to release the
offline memcg to ensure the next memcg stored in the cursor is online.
The offline memcg cleaner has also been changed to avoid the same issue.
When the next memcg of the offlined memcg is also offline, the refcount
stored in the iteration cursor was held until the next shrink_worker()
run. The cleaner must release the offline memcg recursively.
[yosryahmed@google.com: make critical section more obvious, unify comments]
Link: https://lkml.kernel.org/r/CAJD7tkaScz+SbB90Q1d5mMD70UfM2a-J2zhXDT9sePR7Qap45Q@mail.gmail.com
Link: https://lkml.kernel.org/r/20240731004918.33182-1-flintglass@gmail.com
Link: https://lkml.kernel.org/r/20240731004918.33182-2-flintglass@gmail.com
Fixes:
|
||
|
Dan Carpenter
|
b749cb0d61 |
mm/zswap: fix a white space issue
We accidentally deleted a tab in commit f84152e9efc5 ("mm/zswap: use only
one pool in zswap"). Add it back.
Link: https://lkml.kernel.org/r/c15066a0-f061-42c9-b0f5-d60281d3d5d8@stanley.mountain
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Reviewed-by: Chengming Zhou <chengming.zhou@linux.dev>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
|
||
|
Chengming Zhou
|
8edc9c4e72 |
mm/zswap: use only one pool in zswap
Zswap uses 32 pools to workaround the locking scalability problem in zswap
backends (mainly zsmalloc nowadays), which brings its own problems like
memory waste and more memory fragmentation.
Testing results show that we can have near performance with only one pool
in zswap after changing zsmalloc to use per-size_class lock instead of
pool spinlock.
Testing kernel build (make bzImage -j32) on tmpfs with memory.max=1GB, and
zswap shrinker enabled with 10GB swapfile on ext4.
real user sys
6.10.0-rc3 138.18 1241.38 1452.73
6.10.0-rc3-onepool 149.45 1240.45 1844.69
6.10.0-rc3-onepool-perclass 138.23 1242.37 1469.71
And do the same testing using zbud, which shows a little worse performance
as expected since we don't do any locking optimization for zbud. I think
it's acceptable since zsmalloc became a lot more popular than other
backends, and we may want to support only zsmalloc in the future.
real user sys
6.10.0-rc3-zbud 138.23 1239.58 1430.09
6.10.0-rc3-onepool-zbud 139.64 1241.37 1516.59
[chengming.zhou@linux.dev: fix error handling in zswap_pool_create(), per Dan Carpenter]
Link: https://lkml.kernel.org/r/20240621-zsmalloc-lock-mm-everything-v2-2-d30e9cd2b793@linux.dev
[chengming.zhou@linux.dev: fix error handling again in zswap_pool_create(), per Yosry]
Link: https://lkml.kernel.org/r/20240625-zsmalloc-lock-mm-everything-v3-2-ad941699cb61@linux.dev
Link: https://lkml.kernel.org/r/20240617-zsmalloc-lock-mm-everything-v1-2-5e5081ea11b3@linux.dev
Signed-off-by: Chengming Zhou <chengming.zhou@linux.dev>
Reviewed-by: Nhat Pham <nphamcs@gmail.com>
Acked-by: Yosry Ahmed <yosryahmed@google.com>
Cc: Chengming Zhou <zhouchengming@bytedance.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Sergey Senozhatsky <senozhatsky@chromium.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
|
||
|
Yosry Ahmed
|
c63f210d48 |
mm: zswap: handle incorrect attempts to load large folios
Zswap does not support storing or loading large folios. Until proper
support is added, attempts to load large folios from zswap are a bug.
For example, if a swapin fault observes that contiguous PTEs are pointing
to contiguous swap entries and tries to swap them in as a large folio,
swap_read_folio() will pass in a large folio to zswap_load(), but
zswap_load() will only effectively load the first page in the folio. If
the first page is not in zswap, the folio will be read from disk, even
though other pages may be in zswap.
In both cases, this will lead to silent data corruption. Proper support
needs to be added before large folio swapins and zswap can work together.
Looking at callers of swap_read_folio(), it seems like they are either
allocated from __read_swap_cache_async() or do_swap_page() in the
SWP_SYNCHRONOUS_IO path. Both of which allocate order-0 folios, so
everything is fine for now.
However, there is ongoing work to add to support large folio swapins [1].
To make sure new development does not break zswap (or get broken by
zswap), add minimal handling of incorrect loads of large folios to zswap.
First, move the call folio_mark_uptodate() inside zswap_load().
If a large folio load is attempted, and zswap was ever enabled on the
system, return 'true' without calling folio_mark_uptodate(). This will
prevent the folio from being read from disk, and will emit an IO error
because the folio is not uptodate (e.g. do_swap_fault() will return
VM_FAULT_SIGBUS). It may not be reliable recovery in all cases, but it is
better than nothing.
This was tested by hacking the allocation in __read_swap_cache_async() to
use order 2 and __GFP_COMP.
In the future, to handle this correctly, the swapin code should:
(a) Fall back to order-0 swapins if zswap was ever used on the
machine, because compressed pages remain in zswap after it is
disabled.
(b) Add proper support to swapin large folios from zswap (fully or
partially).
Probably start with (a) then followup with (b).
[1]https://lore.kernel.org/linux-mm/20240304081348.197341-6-21cnbao@gmail.com/
Link: https://lkml.kernel.org/r/20240611024516.1375191-3-yosryahmed@google.com
Signed-off-by: Yosry Ahmed <yosryahmed@google.com>
Acked-by: Barry Song <baohua@kernel.org>
Cc: Barry Song <baohua@kernel.org>
Cc: Chengming Zhou <chengming.zhou@linux.dev>
Cc: Chris Li <chrisl@kernel.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Nhat Pham <nphamcs@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
|
||
|
Yosry Ahmed
|
2d4d2b1cfb |
mm: zswap: add zswap_never_enabled()
Add zswap_never_enabled() to skip the xarray lookup in zswap_load() if zswap was never enabled on the system. It is implemented using static branches for efficiency, as enabling zswap should be a rare event. This could shave some cycles off zswap_load() when CONFIG_ZSWAP is used but zswap is never enabled. However, the real motivation behind this patch is two-fold: - Incoming large folio swapin work will need to fallback to order-0 folios if zswap was ever enabled, because any part of the folio could be in zswap, until proper handling of large folios with zswap is added. - A warning and recovery attempt will be added in a following change in case the above was not done incorrectly. Zswap will fail the read if the folio is large and it was ever enabled. Expose zswap_never_enabled() in the header for the swapin work to use it later. [yosryahmed@google.com: expose zswap_never_enabled() in the header] Link: https://lkml.kernel.org/r/Zmjf0Dr8s9xSW41X@google.com Link: https://lkml.kernel.org/r/20240611024516.1375191-2-yosryahmed@google.com Signed-off-by: Yosry Ahmed <yosryahmed@google.com> Reviewed-by: Nhat Pham <nphamcs@gmail.com> Cc: Barry Song <baohua@kernel.org> Cc: Chengming Zhou <chengming.zhou@linux.dev> Cc: Chris Li <chrisl@kernel.org> Cc: David Hildenbrand <david@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> |
||
|
Yosry Ahmed
|
2b33a97c94 |
mm: zswap: rename is_zswap_enabled() to zswap_is_enabled()
In preparation for introducing a similar function, rename is_zswap_enabled() to use zswap_* prefix like other zswap functions. Link: https://lkml.kernel.org/r/20240611024516.1375191-1-yosryahmed@google.com Signed-off-by: Yosry Ahmed <yosryahmed@google.com> Reviewed-by: Barry Song <baohua@kernel.org> Reviewed-by: Nhat Pham <nphamcs@gmail.com> Cc: Chengming Zhou <chengming.zhou@linux.dev> Cc: Chris Li <chrisl@kernel.org> Cc: David Hildenbrand <david@redhat.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> |
||
|
Yosry Ahmed
|
5a3f572a59 |
mm: zswap: make same_filled functions folio-friendly
A variable name 'page' is used in zswap_is_folio_same_filled() and zswap_fill_page() to point at the kmapped data in a folio. Use 'data' instead to avoid confusion and stop it from showing up when searching for 'page' references in mm/zswap.c. While we are at it, move the kmap/kunmap calls into zswap_fill_page(), make it take in a folio, and rename it to zswap_fill_folio(). Link: https://lkml.kernel.org/r/20240524033819.1953587-4-yosryahmed@google.com Signed-off-by: Yosry Ahmed <yosryahmed@google.com> Reviewed-by: Chengming Zhou <chengming.zhou@linux.dev> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Matthew Wilcox <willy@infradead.org> Cc: Nhat Pham <nphamcs@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> |
||
|
Yosry Ahmed
|
30a28baafc |
mm :zswap: use kmap_local_folio() in zswap_load()
Eliminate the last explicit 'struct page' reference in mm/zswap.c. Link: https://lkml.kernel.org/r/20240524033819.1953587-3-yosryahmed@google.com Signed-off-by: Yosry Ahmed <yosryahmed@google.com> Reviewed-by: Chengming Zhou <chengming.zhou@linux.dev> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Matthew Wilcox <willy@infradead.org> Cc: Nhat Pham <nphamcs@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> |
||
|
Yosry Ahmed
|
5d19f5de67 |
mm: zswap: use sg_set_folio() in zswap_{compress/decompress}()
Patch series "mm: zswap: trivial folio conversions". Some trivial folio conversions in zswap code. This patch (of 3): sg_set_folio() is equivalent to sg_set_page() for order-0 folios, which are the only ones supported by zswap. Now zswap_decompress() can take in a folio directly. Link: https://lkml.kernel.org/r/20240524033819.1953587-1-yosryahmed@google.com Link: https://lkml.kernel.org/r/20240524033819.1953587-2-yosryahmed@google.com Signed-off-by: Yosry Ahmed <yosryahmed@google.com> Reviewed-by: Chengming Zhou <chengming.zhou@linux.dev> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Matthew Wilcox <willy@infradead.org> Cc: Nhat Pham <nphamcs@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> |
||
|
Yosry Ahmed
|
c074e1467f |
mm: zswap: remove same_filled module params
These knobs offer more fine-grained control to userspace than needed and
directly expose/influence kernel implementation; remove them.
For disabling same_filled handling, there is no logical reason to refuse
storing same-filled pages more efficiently and opt for compression.
Scanning pages for patterns may be an argument, but the page contents will
be read into the CPU cache anyway during compression. Also, removing the
same_filled handling code does not move the needle significantly in terms
of performance anyway [1].
For disabling non_same_filled handling, it was added when the compressed
pages in zswap were not being properly charged to memcgs, as workloads
could escape the accounting with compression [2]. This is no longer the
case after commit
|
||
|
Yosry Ahmed
|
e87b881489 |
mm: zswap: move more same-filled pages checks outside of zswap_store()
Currently, zswap_store() checks zswap_same_filled_pages_enabled, kmaps the folio, then calls zswap_is_page_same_filled() to check the folio contents. Move this logic into zswap_is_page_same_filled() as well (and rename it to use 'folio' while we are at it). This makes zswap_store() cleaner, and makes following changes to that logic contained within the helper. While we are at it: - Rename the insert_entry label to store_entry to match xa_store(). - Add comment headers for same-filled functions and the main API functions (load, store, invalidate, swapon, swapoff). No functional change intended. Link: https://lkml.kernel.org/r/20240413022407.785696-4-yosryahmed@google.com Signed-off-by: Yosry Ahmed <yosryahmed@google.com> Reviewed-by: Nhat Pham <nphamcs@gmail.com> Reviewed-by: Chengming Zhou <chengming.zhou@linux.dev> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: "Maciej S. Szmigiero" <mail@maciej.szmigiero.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> |
||
|
Yosry Ahmed
|
82e0f8e47b |
mm: zswap: refactor limit checking from zswap_store()
Refactor limit and acceptance threshold checking outside of zswap_store(). This code will be moved around in a following patch, so it would be cleaner to move a function call around. Link: https://lkml.kernel.org/r/20240413022407.785696-3-yosryahmed@google.com Signed-off-by: Yosry Ahmed <yosryahmed@google.com> Reviewed-by: Nhat Pham <nphamcs@gmail.com> Cc: Chengming Zhou <chengming.zhou@linux.dev> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: "Maciej S. Szmigiero" <mail@maciej.szmigiero.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> |
||
|
Yosry Ahmed
|
4ea3fa9dd2 |
mm: zswap: always shrink in zswap_store() if zswap_pool_reached_full
Patch series "zswap same-filled and limit checking cleanups", v3. Miscellaneous cleanups for limit checking and same-filled handling in the store path. This series was broken out of the "zswap: store zero-filled pages more efficiently" series [1]. It contains the cleanups and drops the main functional changes. [1]https://lore.kernel.org/lkml/20240325235018.2028408-1-yosryahmed@google.com/ This patch (of 4): The cleanup code in zswap_store() is not pretty, particularly the 'shrink' label at the bottom that ends up jumping between cleanup labels. Instead of having a dedicated label to shrink the pool, just use zswap_pool_reached_full directly to figure out if the pool needs shrinking. zswap_pool_reached_full should be true if and only if the pool needs shrinking. The only caveat is that the value of zswap_pool_reached_full may be changed by concurrent zswap_store() calls between checking the limit and testing zswap_pool_reached_full in the cleanup code. This is fine because: - If zswap_pool_reached_full was true during limit checking then became false during the cleanup code, then someone else already took care of shrinking the pool and there is no need to queue the worker. That would be a good change. - If zswap_pool_reached_full was false during limit checking then became true during the cleanup code, then someone else hit the limit meanwhile. In this case, both threads will try to queue the worker, but it never gets queued more than once anyway. Also, calling queue_work() multiple times when the limit is hit could already happen today, so this isn't a significant change in any way. Link: https://lkml.kernel.org/r/20240413022407.785696-1-yosryahmed@google.com Link: https://lkml.kernel.org/r/20240413022407.785696-2-yosryahmed@google.com Signed-off-by: Yosry Ahmed <yosryahmed@google.com> Reviewed-by: Nhat Pham <nphamcs@gmail.com> Reviewed-by: Chengming Zhou <chengming.zhou@linux.dev> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: "Maciej S. Szmigiero" <mail@maciej.szmigiero.name> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> |
||
|
Chris Li
|
796c2c23e1 |
zswap: replace RB tree with xarray
Very deep RB tree requires rebalance at times. That contributes to the
zswap fault latencies. Xarray does not need to perform tree rebalance.
Replacing RB tree to xarray can have some small performance gain.
One small difference is that xarray insert might fail with ENOMEM, while
RB tree insert does not allocate additional memory.
The zswap_entry size will reduce a bit due to removing the RB node, which
has two pointers and a color field. Xarray store the pointer in the
xarray tree rather than the zswap_entry. Every entry has one pointer from
the xarray tree. Overall, switching to xarray should save some memory, if
the swap entries are densely packed.
Notice the zswap_rb_search and zswap_rb_insert often followed by
zswap_rb_erase. Use xa_erase and xa_store directly. That saves one tree
lookup as well.
Remove zswap_invalidate_entry due to no need to call zswap_rb_erase any
more. Use zswap_free_entry instead.
The "struct zswap_tree" has been replaced by "struct xarray". The tree
spin lock has transferred to the xarray lock.
Run the kernel build testing 5 times for each version, averages:
(memory.max=2GB, zswap shrinker and writeback enabled, one 50GB swapfile,
24 HT core, 32 jobs)
mm-unstable-4aaccadb5c04 xarray v9
user 3548.902 3534.375
sys 522.232 520.976
real 202.796 200.864
[chrisl@kernel.org: restore original comment "erase" to "invalidate"]
Link: https://lkml.kernel.org/r/20240326-zswap-xarray-v10-1-bf698417c968@kernel.org
Link: https://lkml.kernel.org/r/20240326-zswap-xarray-v9-1-d2891a65dfc7@kernel.org
Signed-off-by: Chris Li <chrisl@kernel.org>
Acked-by: Yosry Ahmed <yosryahmed@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Nhat Pham <nphamcs@gmail.com>
Cc: Barry Song <v-songbaohua@oppo.com>
Cc: Chengming Zhou <zhouchengming@bytedance.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
|
||
|
Yosry Ahmed
|
cc9bc36ebe |
mm: zswap: remove nr_zswap_stored atomic
nr_stored was introduced by commit |
||
|
Yosry Ahmed
|
fea68a7565 |
mm: zswap: remove unnecessary check in zswap_find_zpool()
zswap_find_zpool() checks if ZSWAP_NR_ZPOOLS > 1, which is always true. This is a remnant from a patch version that had ZSWAP_NR_ZPOOLS as a config option and never made it upstream. Remove the unnecessary check. Link: https://lkml.kernel.org/r/20240311235210.2937484-1-yosryahmed@google.com Signed-off-by: Yosry Ahmed <yosryahmed@google.com> Reviewed-by: Chengming Zhou <chengming.zhou@linux.dev> Reviewed-by: Nhat Pham <nphamcs@gmail.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Yosry Ahmed <yosryahmed@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> |
||
|
Johannes Weiner
|
4196b48ddd |
mm: zpool: return pool size in pages
All zswap backends track their pool sizes in pages. Currently they multiply by PAGE_SIZE for zswap, only for zswap to divide again in order to do limit math. Report pages directly. Link: https://lkml.kernel.org/r/20240312153901.3441-2-hannes@cmpxchg.org Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Yosry Ahmed <yosryahmed@google.com> Reviewed-by: Chengming Zhou <chengming.zhou@linux.dev> Reviewed-by: Nhat Pham <nphamcs@gmail.com> Cc: Yosry Ahmed <yosryahmed@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> |
||
|
Johannes Weiner
|
91cdcd8d62 |
mm: zswap: optimize zswap pool size tracking
Profiling the munmap() of a zswapped memory region shows 60% of the total
cycles currently going into updating the zswap_pool_total_size.
There are three consumers of this counter:
- store, to enforce the globally configured pool limit
- meminfo & debugfs, to report the size to the user
- shrink, to determine the batch size for each cycle
Instead of aggregating everytime an entry enters or exits the zswap
pool, aggregate the value from the zpools on-demand:
- Stores aggregate the counter anyway upon success. Aggregating to
check the limit instead is the same amount of work.
- Meminfo & debugfs might benefit somewhat from a pre-aggregated
counter, but aren't exactly hotpaths.
- Shrinking can aggregate once for every cycle instead of doing it for
every freed entry. As the shrinker might work on tens or hundreds of
objects per scan cycle, this is a large reduction in aggregations.
The paths that benefit dramatically are swapin, swapoff, and unmaps.
There could be millions of pages being processed until somebody asks for
the pool size again. This eliminates the pool size updates from those
paths entirely.
Top profile entries for a 24G range munmap(), before:
38.54% zswap-unmap [kernel.kallsyms] [k] zs_zpool_total_size
12.51% zswap-unmap [kernel.kallsyms] [k] zpool_get_total_size
9.10% zswap-unmap [kernel.kallsyms] [k] zswap_update_total_size
2.95% zswap-unmap [kernel.kallsyms] [k] obj_cgroup_uncharge_zswap
2.88% zswap-unmap [kernel.kallsyms] [k] __slab_free
2.86% zswap-unmap [kernel.kallsyms] [k] xas_store
and after:
7.70% zswap-unmap [kernel.kallsyms] [k] __slab_free
7.16% zswap-unmap [kernel.kallsyms] [k] obj_cgroup_uncharge_zswap
6.74% zswap-unmap [kernel.kallsyms] [k] xas_store
It was also briefly considered to move to a single atomic in zswap
that is updated by the backends, since zswap only cares about the sum
of all pools anyway. However, zram directly needs per-pool information
out of zsmalloc. To keep the backend from having to update two atomics
every time, I opted for the lazy aggregation instead for now.
Link: https://lkml.kernel.org/r/20240312153901.3441-1-hannes@cmpxchg.org
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Yosry Ahmed <yosryahmed@google.com>
Reviewed-by: Chengming Zhou <chengming.zhou@linux.dev>
Reviewed-by: Nhat Pham <nphamcs@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
|
||
|
Yosry Ahmed
|
91b71e78b8 |
mm: memcg: add NULL check to obj_cgroup_put()
9 out of 16 callers perform a NULL check before calling obj_cgroup_put(). Move the NULL check in the function, similar to mem_cgroup_put(). The unlikely() NULL check in current_objcg_update() was left alone to avoid dropping the unlikey() annotation as this a fast path. Link: https://lkml.kernel.org/r/20240316015803.2777252-1-yosryahmed@google.com Signed-off-by: Yosry Ahmed <yosryahmed@google.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Roman Gushchin <roman.gushchin@linux.dev> Cc: Michal Hocko <mhocko@kernel.org> Cc: Muchun Song <muchun.song@linux.dev> Cc: Shakeel Butt <shakeel.butt@linux.dev> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> |
||
|
Johannes Weiner
|
682886ec69 |
mm: zswap: fix shrinker NULL crash with cgroup_disable=memory
Christian reports a NULL deref in zswap that he bisected down to the zswap
shrinker. The issue also cropped up in the bug trackers of libguestfs [1]
and the Red Hat bugzilla [2].
The problem is that when memcg is disabled with the boot time flag, the
zswap shrinker might get called with sc->memcg == NULL. This is okay in
many places, like the lruvec operations. But it crashes in
memcg_page_state() - which is only used due to the non-node accounting of
cgroup's the zswap memory to begin with.
Nhat spotted that the memcg can be NULL in the memcg-disabled case, and I
was then able to reproduce the crash locally as well.
[1] https://github.com/libguestfs/libguestfs/issues/139
[2] https://bugzilla.redhat.com/show_bug.cgi?id=2275252
Link: https://lkml.kernel.org/r/20240418124043.GC1055428@cmpxchg.org
Link: https://lkml.kernel.org/r/20240417143324.GA1055428@cmpxchg.org
Fixes:
|
||
|
Johannes Weiner
|
25cd241408 |
mm: zswap: fix data loss on SWP_SYNCHRONOUS_IO devices
Zhongkun He reports data corruption when combining zswap with zram.
The issue is the exclusive loads we're doing in zswap. They assume
that all reads are going into the swapcache, which can assume
authoritative ownership of the data and so the zswap copy can go.
However, zram files are marked SWP_SYNCHRONOUS_IO, and faults will try to
bypass the swapcache. This results in an optimistic read of the swap data
into a page that will be dismissed if the fault fails due to races. In
this case, zswap mustn't drop its authoritative copy.
Link: https://lore.kernel.org/all/CACSyD1N+dUvsu8=zV9P691B9bVq33erwOXNTmEaUbi9DrDeJzw@mail.gmail.com/
Fixes:
|
||
|
Johannes Weiner
|
30fb6a8d9e |
mm: zswap: fix writeback shinker GFP_NOIO/GFP_NOFS recursion
Kent forwards this bug report of zswap re-entering the block layer
from an IO request allocation and locking up:
[10264.128242] sysrq: Show Blocked State
[10264.128268] task:kworker/20:0H state:D stack:0 pid:143 tgid:143 ppid:2 flags:0x00004000
[10264.128271] Workqueue: bcachefs_io btree_write_submit [bcachefs]
[10264.128295] Call Trace:
[10264.128295] <TASK>
[10264.128297] __schedule+0x3e6/0x1520
[10264.128303] schedule+0x32/0xd0
[10264.128304] schedule_timeout+0x98/0x160
[10264.128308] io_schedule_timeout+0x50/0x80
[10264.128309] wait_for_completion_io_timeout+0x7f/0x180
[10264.128310] submit_bio_wait+0x78/0xb0
[10264.128313] swap_writepage_bdev_sync+0xf6/0x150
[10264.128317] zswap_writeback_entry+0xf2/0x180
[10264.128319] shrink_memcg_cb+0xe7/0x2f0
[10264.128322] __list_lru_walk_one+0xb9/0x1d0
[10264.128325] list_lru_walk_one+0x5d/0x90
[10264.128326] zswap_shrinker_scan+0xc4/0x130
[10264.128327] do_shrink_slab+0x13f/0x360
[10264.128328] shrink_slab+0x28e/0x3c0
[10264.128329] shrink_one+0x123/0x1b0
[10264.128331] shrink_node+0x97e/0xbc0
[10264.128332] do_try_to_free_pages+0xe7/0x5b0
[10264.128333] try_to_free_pages+0xe1/0x200
[10264.128334] __alloc_pages_slowpath.constprop.0+0x343/0xde0
[10264.128337] __alloc_pages+0x32d/0x350
[10264.128338] allocate_slab+0x400/0x460
[10264.128339] ___slab_alloc+0x40d/0xa40
[10264.128345] kmem_cache_alloc+0x2e7/0x330
[10264.128348] mempool_alloc+0x86/0x1b0
[10264.128349] bio_alloc_bioset+0x200/0x4f0
[10264.128352] bio_alloc_clone+0x23/0x60
[10264.128354] alloc_io+0x26/0xf0 [dm_mod 7e9e6b44df4927f93fb3e4b5c782767396f58382]
[10264.128361] dm_submit_bio+0xb8/0x580 [dm_mod 7e9e6b44df4927f93fb3e4b5c782767396f58382]
[10264.128366] __submit_bio+0xb0/0x170
[10264.128367] submit_bio_noacct_nocheck+0x159/0x370
[10264.128368] bch2_submit_wbio_replicas+0x21c/0x3a0 [bcachefs 85f1b9a7a824f272eff794653a06dde1a94439f2]
[10264.128391] btree_write_submit+0x1cf/0x220 [bcachefs 85f1b9a7a824f272eff794653a06dde1a94439f2]
[10264.128406] process_one_work+0x178/0x350
[10264.128408] worker_thread+0x30f/0x450
[10264.128409] kthread+0xe5/0x120
The zswap shrinker resumes the swap_writepage()s that were intercepted
by the zswap store. This will enter the block layer, and may even
enter the filesystem depending on the swap backing file.
Make it respect GFP_NOIO and GFP_NOFS.
Link: https://lore.kernel.org/linux-mm/rc4pk2r42oyvjo4dc62z6sovquyllq56i5cdgcaqbd7wy3hfzr@n4nbxido3fme/
Link: https://lkml.kernel.org/r/20240321182532.60000-1-hannes@cmpxchg.org
Fixes:
|
||
|
Barry Song
|
9c500835f2 |
mm: zswap: fix kernel BUG in sg_init_one
sg_init_one() relies on linearly mapped low memory for the safe utilization of virt_to_page(). Otherwise, we trigger a kernel BUG, kernel BUG at include/linux/scatterlist.h:187! Internal error: Oops - BUG: 0 [#1] PREEMPT SMP ARM Modules linked in: CPU: 0 PID: 2997 Comm: syz-executor198 Not tainted 6.8.0-syzkaller #0 Hardware name: ARM-Versatile Express PC is at sg_set_buf include/linux/scatterlist.h:187 [inline] PC is at sg_init_one+0x9c/0xa8 lib/scatterlist.c:143 LR is at sg_init_table+0x2c/0x40 lib/scatterlist.c:128 Backtrace: [<807e16ac>] (sg_init_one) from [<804c1824>] (zswap_decompress+0xbc/0x208 mm/zswap.c:1089) r7:83471c80 r6:def6d08c r5:844847d0 r4:ff7e7ef4 [<804c1768>] (zswap_decompress) from [<804c4468>] (zswap_load+0x15c/0x198 mm/zswap.c:1637) r9:8446eb80 r8:8446eb80 r7:8446eb84 r6:def6d08c r5:00000001 r4:844847d0 [<804c430c>] (zswap_load) from [<804b9644>] (swap_read_folio+0xa8/0x498 mm/page_io.c:518) r9:844ac800 r8:835e6c00 r7:00000000 r6:df955d4c r5:00000001 r4:def6d08c [<804b959c>] (swap_read_folio) from [<804bb064>] (swap_cluster_readahead+0x1c4/0x34c mm/swap_state.c:684) r10:00000000 r9:00000007 r8:df955d4b r7:00000000 r6:00000000 r5:00100cca r4:00000001 [<804baea0>] (swap_cluster_readahead) from [<804bb3b8>] (swapin_readahead+0x68/0x4a8 mm/swap_state.c:904) r10:df955eb8 r9:00000000 r8:00100cca r7:84476480 r6:00000001 r5:00000000 r4:00000001 [<804bb350>] (swapin_readahead) from [<8047cde0>] (do_swap_page+0x200/0xcc4 mm/memory.c:4046) r10:00000040 r9:00000000 r8:844ac800 r7:84476480 r6:00000001 r5:00000000 r4:df955eb8 [<8047cbe0>] (do_swap_page) from [<8047e6c4>] (handle_pte_fault mm/memory.c:5301 [inline]) [<8047cbe0>] (do_swap_page) from [<8047e6c4>] (__handle_mm_fault mm/memory.c:5439 [inline]) [<8047cbe0>] (do_swap_page) from [<8047e6c4>] (handle_mm_fault+0x3d8/0x12b8 mm/memory.c:5604) r10:00000040 r9:842b3900 r8:7eb0d000 r7:84476480 r6:7eb0d000 r5:835e6c00 r4:00000254 [<8047e2ec>] (handle_mm_fault) from [<80215d28>] (do_page_fault+0x148/0x3a8 arch/arm/mm/fault.c:326) r10:00000007 r9:842b3900 r8:7eb0d000 r7:00000207 r6:00000254 r5:7eb0d9b4 r4:df955fb0 [<80215be0>] (do_page_fault) from [<80216170>] (do_DataAbort+0x38/0xa8 arch/arm/mm/fault.c:558) r10:7eb0da7c r9:00000000 r8:80215be0 r7:df955fb0 r6:7eb0d9b4 r5:00000207 r4:8261d0e0 [<80216138>] (do_DataAbort) from [<80200e3c>] (__dabt_usr+0x5c/0x60 arch/arm/kernel/entry-armv.S:427) Exception stack(0xdf955fb0 to 0xdf955ff8) 5fa0: 00000000 00000000 22d5f800 0008d158 5fc0: 00000000 7eb0d9a4 00000000 00000109 00000000 00000000 7eb0da7c 7eb0da3c 5fe0: 00000000 7eb0d9a0 00000001 00066bd4 00000010 ffffffff r8:824a9044 r7:835e6c00 r6:ffffffff r5:00000010 r4:00066bd4 Code: 1a000004 e1822003 e8860094 e89da8f0 (e7f001f2) ---[ end trace 0000000000000000 ]--- ---------------- Code disassembly (best guess): 0: 1a000004 bne 0x18 4: e1822003 orr r2, r2, r3 8: e8860094 stm r6, {r2, r4, r7} c: e89da8f0 ldm sp, {r4, r5, r6, r7, fp, sp, pc} * 10: e7f001f2 udf #18 <-- trapping instruction Consequently, we have two choices: either employ kmap_to_page() alongside sg_set_page(), or resort to copying high memory contents to a temporary buffer residing in low memory. However, considering the introduction of the WARN_ON_ONCE in commit |
||
|
Barry Song
|
270700dd06 |
mm/zswap: remove the memcpy if acomp is not sleepable
Most compressors are actually CPU-based and won't sleep during compression and decompression. We should remove the redundant memcpy for them. This patch checks if the algorithm is sleepable by testing the CRYPTO_ALG_ASYNC algorithm flag. Generally speaking, async and sleepable are semantically similar but not equal. But for compress drivers, they are basically equal at least due to the below facts. Firstly, scompress drivers - crypto/deflate.c, lz4.c, zstd.c, lzo.c etc have no sleep. Secondly, zRAM has been using these scompress drivers for years in atomic contexts, and never worried those drivers going to sleep. One exception is that an async driver can sometimes still return synchronously per Herbert's clarification. In this case, we are still having a redundant memcpy. But we can't know if one particular acomp request will sleep or not unless crypto can expose more details for each specific request from offload drivers. Link: https://lkml.kernel.org/r/20240222081135.173040-3-21cnbao@gmail.com Signed-off-by: Barry Song <v-songbaohua@oppo.com> Tested-by: Chengming Zhou <zhouchengming@bytedance.com> Reviewed-by: Nhat Pham <nphamcs@gmail.com> Acked-by: Yosry Ahmed <yosryahmed@google.com> Reviewed-by: Chengming Zhou <zhouchengming@bytedance.com> Acked-by: Chris Li <chrisl@kernel.org> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Dan Streetman <ddstreet@ieee.org> Cc: David S. Miller <davem@davemloft.net> Cc: Herbert Xu <herbert@gondor.apana.org.au> Cc: Seth Jennings <sjenning@redhat.com> Cc: Vitaly Wool <vitaly.wool@konsulko.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> |
||
|
Chengming Zhou
|
e35606e416 |
mm/zswap: global lru and shrinker shared by all zswap_pools fix
Commit |
||
|
Chengming Zhou
|
94ace3fec8 |
mm/zswap: change zswap_pool kref to percpu_ref
All zswap entries will take a reference of zswap_pool when zswap_store(),
and drop it when free. Change it to use the percpu_ref is better for
scalability performance.
Although percpu_ref use a bit more memory which should be ok for our use
case, since we almost have only one zswap_pool to be using. The
performance gain is for zswap_store/load hotpath.
Testing kernel build (32 threads) in tmpfs with memory.max=2GB. (zswap
shrinker and writeback enabled with one 50GB swapfile, on a 128 CPUs
x86-64 machine, below is the average of 5 runs)
mm-unstable zswap-global-lru
real 63.20 63.12
user 1061.75 1062.95
sys 268.74 264.44
[chengming.zhou@linux.dev: fix zswap_pools_lock usages after changing to percpu_ref]
Link: https://lkml.kernel.org/r/20240228154954.3028626-1-chengming.zhou@linux.dev
Link: https://lkml.kernel.org/r/20240210-zswap-global-lru-v3-2-200495333595@bytedance.com
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Reviewed-by: Nhat Pham <nphamcs@gmail.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Yosry Ahmed <yosryahmed@google.com>
Cc: Chengming Zhou <chengming.zhou@linux.dev>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
|
||
|
Chengming Zhou
|
bf9b7df23c |
mm/zswap: global lru and shrinker shared by all zswap_pools
Patch series "mm/zswap: optimize for dynamic zswap_pools", v3.
Dynamic pool creation has been supported for a long time, which maybe not
used so much in practice. But with the per-memcg lru merged, the current
structure of zswap_pool's lru and shrinker become less optimal.
In the current structure, each zswap_pool has its own lru, shrinker and
shrink_work, but only the latest zswap_pool will be the current used.
1. When memory has pressure, all shrinkers of zswap_pools will try to
shrink its lru list, there is no order between them.
2. When zswap limit hit, only the last zswap_pool's shrink_work will
try to shrink its own lru, which is inefficient.
A more natural way is to have a global zswap lru shared between all
zswap_pools, and so is the shrinker. The code becomes much simpler too.
Another optimization is changing zswap_pool kref to percpu_ref, which will
be taken reference by every zswap entry. So the scalability is better.
Testing kernel build (32 threads) in tmpfs with memory.max=2GB. (zswap
shrinker and writeback enabled with one 50GB swapfile, on a 128 CPUs
x86-64 machine, below is the average of 5 runs)
mm-unstable zswap-global-lru
real 63.20 63.12
user 1061.75 1062.95
sys 268.74 264.44
This patch (of 3):
Dynamic zswap_pool creation may create/reuse to have multiple zswap_pools
in a list, only the first will be current used.
Each zswap_pool has its own lru and shrinker, which is not necessary and
has its problem:
1. When memory has pressure, all shrinker of zswap_pools will
try to shrink its own lru, there is no order between them.
2. When zswap limit hit, only the last zswap_pool's shrink_work
will try to shrink its lru list. The rationale here was to
try and empty the old pool first so that we can completely
drop it. However, since we only support exclusive loads now,
the LRU ordering should be entirely decided by the order of
stores, so the oldest entries on the LRU will naturally be
from the oldest pool.
Anyway, having a global lru and shrinker shared by all zswap_pools is
better and efficient.
Link: https://lkml.kernel.org/r/20240210-zswap-global-lru-v3-0-200495333595@bytedance.com
Link: https://lkml.kernel.org/r/20240210-zswap-global-lru-v3-1-200495333595@bytedance.com
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Acked-by: Yosry Ahmed <yosryahmed@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Nhat Pham <nphamcs@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
|
||
|
Barry Song
|
55e78c933d |
mm: zswap: increase reject_compress_poor but not reject_compress_fail if compression returns ENOSPC
We used to rely on the returned -ENOSPC of zpool_malloc() to increase reject_compress_poor. But the code wouldn't get to there after commit |
||
|
Chengming Zhou
|
f576a1e80c |
mm/zswap: optimize and cleanup the invalidation of duplicate entry
We may encounter duplicate entry in the zswap_store(): 1. swap slot that freed to per-cpu swap cache, doesn't invalidate the zswap entry, then got reused. This has been fixed. 2. !exclusive load mode, swapin folio will leave its zswap entry on the tree, then swapout again. This has been removed. 3. one folio can be dirtied again after zswap_store(), so need to zswap_store() again. This should be handled correctly. So we must invalidate the old duplicate entry before inserting the new one, which actually doesn't have to be done at the beginning of zswap_store(). The good point is that we don't need to lock the tree twice in the normal store success path. And cleanup the loop as we are here. Note we still need to invalidate the old duplicate entry when store failed or zswap is disabled , otherwise the new data in swapfile could be overwrite by the old data in zswap pool when lru writeback. Link: https://lkml.kernel.org/r/20240209044112.3883835-1-chengming.zhou@linux.dev Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Yosry Ahmed <yosryahmed@google.com> Acked-by: Chris Li <chrisl@kernel.org> Acked-by: Nhat Pham <nphamcs@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> |
||
|
Chengming Zhou
|
a230c20e63 |
mm/zswap: zswap entry doesn't need refcount anymore
Since we don't need to leave zswap entry on the zswap tree anymore, we should remove it from tree once we find it from the tree. Then after using it, we can directly free it, no concurrent path can find it from tree. Only the shrinker can see it from lru list, which will also double check under tree lock, so no race problem. So we don't need refcount in zswap entry anymore and don't need to take the spinlock for the second time to invalidate it. The side effect is that zswap_entry_free() maybe not happen in tree spinlock, but it's ok since nothing need to be protected by the lock. Link: https://lkml.kernel.org/r/20240201-b4-zswap-invalidate-entry-v2-6-99d4084260a0@bytedance.com Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com> Reviewed-by: Nhat Pham <nphamcs@gmail.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Cc: Yosry Ahmed <yosryahmed@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> |
||
|
Chengming Zhou
|
c2e2ba7702 |
mm/zswap: only support zswap_exclusive_loads_enabled
The !zswap_exclusive_loads_enabled mode will leave compressed copy in the zswap tree and lru list after the folio swapin. There are some disadvantages in this mode: 1. It's a waste of memory since there are two copies of data, one is folio, the other one is compressed data in zswap. And it's unlikely the compressed data is useful in the near future. 2. If that folio is dirtied, the compressed data must be not useful, but we don't know and don't invalidate the trashy memory in zswap. 3. It's not reclaimable from zswap shrinker since zswap_writeback_entry() will always return -EEXIST and terminate the shrinking process. On the other hand, the only downside of zswap_exclusive_loads_enabled is a little more cpu usage/latency when compression, and the same if the folio is removed from swapcache or dirtied. More explanation by Johannes on why we should consider exclusive load as the default for zswap: Caching "swapout work" is helpful when the system is thrashing. Then recently swapped in pages might get swapped out again very soon. It certainly makes sense with conventional swap, because keeping a clean copy on the disk saves IO work and doesn't cost any additional memory. But with zswap, it's different. It saves some compression work on a thrashing page. But the act of keeping compressed memory contributes to a higher rate of thrashing. And that can cause IO in other places like zswap writeback and file memory. And the A/B test results of the kernel build in tmpfs with limited memory can support this theory: !exclusive exclusive real 63.80 63.01 user 1063.83 1061.32 sys 290.31 266.15 workingset_refault_anon 2383084.40 1976397.40 workingset_refault_file 44134.00 45689.40 workingset_activate_anon 837878.00 728441.20 workingset_activate_file 4710.00 4085.20 workingset_restore_anon 732622.60 639428.40 workingset_restore_file 1007.00 926.80 workingset_nodereclaim 0.00 0.00 pgscan 14343003.40 12409570.20 pgscan_kswapd 0.00 0.00 pgscan_direct 14343003.40 12409570.20 pgscan_khugepaged 0.00 0.00 Link: https://lkml.kernel.org/r/20240201-b4-zswap-invalidate-entry-v2-5-99d4084260a0@bytedance.com Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com> Acked-by: Yosry Ahmed <yosryahmed@google.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Nhat Pham <nphamcs@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> |
||
|
Chengming Zhou
|
3b631bd065 |
mm/zswap: remove duplicate_entry debug value
cat /sys/kernel/debug/zswap/duplicate_entry 2086447 When testing, the duplicate_entry value is very high, but no warning message in the kernel log. From the comment of duplicate_entry "Duplicate store was encountered (rare)", it seems something goes wrong. Actually it's incremented in the beginning of zswap_store(), which found its zswap entry has already on the tree. And this is a normal case, since the folio could leave zswap entry on the tree after swapin, later it's dirtied and swapout/zswap_store again, found its original zswap entry. So duplicate_entry should be only incremented in the real bug case, which already have "WARN_ON(1)", it looks redundant to count bug case, so this patch just remove it. Link: https://lkml.kernel.org/r/20240201-b4-zswap-invalidate-entry-v2-4-99d4084260a0@bytedance.com Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Reviewed-by: Nhat Pham <nphamcs@gmail.com> Acked-by: Yosry Ahmed <yosryahmed@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> |
||
|
Chengming Zhou
|
b49547ade3 |
mm/zswap: stop lru list shrinking when encounter warm region
When the shrinker encounter an existing folio in swap cache, it means we are shrinking into the warmer region. We should terminate shrinking if we're in the dynamic shrinker context. This patch add LRU_STOP to support this, to avoid overshrinking. Link: https://lkml.kernel.org/r/20240201-b4-zswap-invalidate-entry-v2-3-99d4084260a0@bytedance.com Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com> Acked-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Nhat Pham <nphamcs@gmail.com> Reviewed-by: Yosry Ahmed <yosryahmed@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> |
||
|
Chengming Zhou
|
0827a1fb14 |
mm/zswap: invalidate zswap entry when swap entry free
During testing I found there are some times the zswap_writeback_entry()
return -ENOMEM, which is not we expected:
bpftrace -e 'kr:zswap_writeback_entry {@[(int32)retval]=count()}'
@[-12]: 1563
@[0]: 277221
The reason is that __read_swap_cache_async() return NULL because
swapcache_prepare() failed. The reason is that we won't invalidate zswap
entry when swap entry freed to the per-cpu pool, these zswap entries are
still on the zswap tree and lru list.
This patch moves the invalidation ahead to when swap entry freed to the
per-cpu pool, since there is no any benefit to leave trashy zswap entry on
the tree and lru list.
With this patch:
bpftrace -e 'kr:zswap_writeback_entry {@[(int32)retval]=count()}'
@[0]: 259744
Note: large folio can't have zswap entry for now, so don't bother
to add zswap entry invalidation in the large folio swap free path.
Link: https://lkml.kernel.org/r/20240201-b4-zswap-invalidate-entry-v2-2-99d4084260a0@bytedance.com
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Reviewed-by: Nhat Pham <nphamcs@gmail.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Yosry Ahmed <yosryahmed@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
|
||
|
Chengming Zhou
|
f9c0f1c32c |
mm/zswap: add more comments in shrink_memcg_cb()
Patch series "mm/zswap: optimize zswap lru list", v2.
This series is motivated when observe the zswap lru list shrinking, noted
there are some unexpected cases in zswap_writeback_entry().
bpftrace -e 'kr:zswap_writeback_entry {@[(int32)retval]=count()}'
There are some -ENOMEM because when the swap entry is freed to per-cpu
swap pool, it doesn't invalidate/drop zswap entry. Then the shrinker
encounter these trashy zswap entries, it can't be reclaimed and return
-ENOMEM.
So move the invalidation ahead to when swap entry freed to the per-cpu
swap pool, since there is no any benefit to leave trashy zswap entries on
the zswap tree and lru list.
Another case is -EEXIST, which is seen more in the case of
!zswap_exclusive_loads_enabled, in which case the swapin folio will leave
compressed copy on the tree and lru list. And it can't be reclaimed until
the folio is removed from swapcache.
Changing to zswap_exclusive_loads_enabled mode will invalidate when folio
swapin, which has its own drawback if that folio is still clean in
swapcache and swapout again, we need to compress it again. Please see the
commit for details on why we choose exclusive load as the default for
zswap.
Another optimization for -EEXIST is that we add LRU_STOP to support
terminating the shrinking process to avoid evicting warmer region.
Testing using kernel build in tmpfs, one 50GB swapfile and
zswap shrinker_enabled, with memory.max set to 2GB.
mm-unstable zswap-optimize
real 63.90s 63.25s
user 1064.05s 1063.40s
sys 292.32s 270.94s
The main optimization is in sys cpu, about 7% improvement.
This patch (of 6):
Add more comments in shrink_memcg_cb() to describe the deref dance which
is implemented to fix race problem between lru writeback and swapoff, and
the reason why we rotate the entry at the beginning.
Also fix the stale comments in zswap_writeback_entry(), and add more
comments to state that we only deref the tree after we get the swapcache
reference.
Link: https://lkml.kernel.org/r/20240201-b4-zswap-invalidate-entry-v2-0-99d4084260a0@bytedance.com
Link: https://lkml.kernel.org/r/20240201-b4-zswap-invalidate-entry-v2-1-99d4084260a0@bytedance.com
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Suggested-by: Yosry Ahmed <yosryahmed@google.com>
Suggested-by: Johannes Weiner <hannes@cmpxchg.org>
Acked-by: Yosry Ahmed <yosryahmed@google.com>
Reviewed-by: Nhat Pham <nphamcs@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
|