[v1,0/5] percpu: partial chunk depopulation

Message

Roman Gushchin April 1, 2021, 9:42 p.m. UTC

In our production experience the percpu memory allocator is sometimes struggling
with returning the memory to the system. A typical example is a creation of
several thousands memory cgroups (each has several chunks of the percpu data
used for vmstats, vmevents, ref counters etc). Deletion and complete releasing
of these cgroups doesn't always lead to a shrinkage of the percpu memory.

The underlying problem is the fragmentation: to release an underlying chunk
all percpu allocations should be released first. The percpu allocator tends
to top up chunks to improve the utilization. It means new small-ish allocations
(e.g. percpu ref counters) are placed onto almost filled old-ish chunks,
effectively pinning them in memory.

This patchset pretends to solve this problem by implementing a partial
depopulation of percpu chunks: chunks with many empty pages are being
asynchronously depopulated and the pages are returned to the system.

To illustrate the problem the following script can be used:

--
#!/bin/bash

cd /sys/fs/cgroup

mkdir percpu_test
echo "+memory" > percpu_test/cgroup.subtree_control

cat /proc/meminfo | grep Percpu

for i in `seq 1 1000`; do
    mkdir percpu_test/cg_"${i}"
    for j in `seq 1 10`; do
	mkdir percpu_test/cg_"${i}"_"${j}"
    done
done

cat /proc/meminfo | grep Percpu

for i in `seq 1 1000`; do
    for j in `seq 1 10`; do
	rmdir percpu_test/cg_"${i}"_"${j}"
    done
done

sleep 10

cat /proc/meminfo | grep Percpu

for i in `seq 1 1000`; do
    rmdir percpu_test/cg_"${i}"
done

rmdir percpu_test
--

It creates 11000 memory cgroups and removes every 10 out of 11.
It prints the initial size of the percpu memory, the size after
creating all cgroups and the size after deleting most of them.

Results:
  vanilla:
    ./percpu_test.sh
    Percpu:             7488 kB
    Percpu:           481152 kB
    Percpu:           481152 kB

  with this patchset applied:
    ./percpu_test.sh
    Percpu:             7488 kB
    Percpu:           481408 kB
    Percpu:           159488 kB

So the total size of the percpu memory was reduced by 3 times.

v2:
  - depopulation heuristics changed and optimized
  - chunks are put into a separate list, depopulation scan this list
  - chunk->isolated is introduced, chunk->depopulate is dropped
  - rearranged patches a bit
  - fixed a panic discovered by krobot
  - made pcpu_nr_empty_pop_pages per chunk type
  - minor fixes

rfc:
  https://lwn.net/Articles/850508/


Roman Gushchin (5):
  percpu: split __pcpu_balance_workfn()
  percpu: make pcpu_nr_empty_pop_pages per chunk type
  percpu: generalize pcpu_balance_populated()
  percpu: fix a comment about the chunks ordering
  percpu: implement partial chunk depopulation

 mm/percpu-internal.h |   3 +-
 mm/percpu-stats.c    |   9 +-
 mm/percpu.c          | 219 ++++++++++++++++++++++++++++++++++---------
 3 files changed, 182 insertions(+), 49 deletions(-)

Comments

Vlastimil Babka April 7, 2021, 11:09 a.m. UTC | #1

On 4/1/21 11:42 PM, Roman Gushchin wrote:
> In our production experience the percpu memory allocator is sometimes struggling
> with returning the memory to the system. A typical example is a creation of
> several thousands memory cgroups (each has several chunks of the percpu data
> used for vmstats, vmevents, ref counters etc). Deletion and complete releasing
> of these cgroups doesn't always lead to a shrinkage of the percpu memory.
> 
> The underlying problem is the fragmentation: to release an underlying chunk
> all percpu allocations should be released first. The percpu allocator tends
> to top up chunks to improve the utilization. It means new small-ish allocations
> (e.g. percpu ref counters) are placed onto almost filled old-ish chunks,
> effectively pinning them in memory.
> 
> This patchset pretends to solve this problem by implementing a partial

Really "pretends"? :) Or did you mean "attempts"?