Re: [PATCH 00/11] mm: fix page aging across multiple cgroups

[Johannes Weiner <hannes@cmpxchg.org>]

On Wed, Nov 06, 2019 at 06:50:25PM -0800, Shakeel Butt wrote:
> On Mon, Jun 3, 2019 at 2:59 PM Johannes Weiner <hannes@cmpxchg.org> wrote:
> >
> > When applications are put into unconfigured cgroups for memory
> > accounting purposes, the cgrouping itself should not change the
> > behavior of the page reclaim code. We expect the VM to reclaim the
> > coldest pages in the system. But right now the VM can reclaim hot
> > pages in one cgroup while there is eligible cold cache in others.
> >
> > This is because one part of the reclaim algorithm isn't truly cgroup
> > hierarchy aware: the inactive/active list balancing. That is the part
> > that is supposed to protect hot cache data from one-off streaming IO.
> >
> > The recursive cgroup reclaim scheme will scan and rotate the physical
> > LRU lists of each eligible cgroup at the same rate in a round-robin
> > fashion, thereby establishing a relative order among the pages of all
> > those cgroups. However, the inactive/active balancing decisions are
> > made locally within each cgroup, so when a cgroup is running low on
> > cold pages, its hot pages will get reclaimed - even when sibling
> > cgroups have plenty of cold cache eligible in the same reclaim run.
> >
> > For example:
> >
> >    [root@ham ~]# head -n1 /proc/meminfo
> >    MemTotal:        1016336 kB
> >
> >    [root@ham ~]# ./reclaimtest2.sh
> >    Establishing 50M active files in cgroup A...
> >    Hot pages cached: 12800/12800 workingset-a
> >    Linearly scanning through 18G of file data in cgroup B:
> >    real    0m4.269s
> >    user    0m0.051s
> >    sys     0m4.182s
> >    Hot pages cached: 134/12800 workingset-a
> >
> 
> Can you share reclaimtest2.sh as well? Maybe a selftest to
> monitor/test future changes.

I wish it were more portable, but it really only does what it says in
the log output, in a pretty hacky way, with all parameters hard-coded
to my test environment:

---

#!/bin/bash

# this should protect workingset-a from workingset-b

set -e
#set -x

echo Establishing 50M active files in cgroup A...
rmdir /cgroup/workingset-a 2>/dev/null || true
mkdir /cgroup/workingset-a
echo $$ > /cgroup/workingset-a/cgroup.procs
rm -f workingset-a
dd of=workingset-a bs=1M count=0 seek=50 2>/dev/null >/dev/null
cat workingset-a > /dev/null
cat workingset-a > /dev/null
cat workingset-a > /dev/null
cat workingset-a > /dev/null
cat workingset-a > /dev/null
cat workingset-a > /dev/null
cat workingset-a > /dev/null
cat workingset-a > /dev/null
echo -n "Hot pages cached: "
./mincore workingset-a

echo -n Linearly scanning through 2G of file data cgroup B:
rmdir /cgroup/workingset-b >/dev/null || true
mkdir /cgroup/workingset-b
echo $$ > /cgroup/workingset-b/cgroup.procs
rm -f workingset-b
dd of=workingset-b bs=1M count=0 seek=2048 2>/dev/null >/dev/null
time (
  cat workingset-b > /dev/null
  cat workingset-b > /dev/null
  cat workingset-b > /dev/null
  cat workingset-b > /dev/null
  cat workingset-b > /dev/null
  cat workingset-b > /dev/null
  cat workingset-b > /dev/null
  cat workingset-b > /dev/null )
echo -n "Hot pages cached: "
./mincore workingset-a