| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <YHm5i9/j+RiKcONf@carbon.dhcp.thefacebook.com>
Date: Fri, 16 Apr 2021 09:21:31 -0700
From: Roman Gushchin <guro@...com>
To: Dennis Zhou <dennis@...nel.org>
CC: Pratik Sampat <psampat@...ux.ibm.com>, Tejun Heo <tj@...nel.org>,
Christoph Lameter <cl@...ux.com>,
Andrew Morton <akpm@...ux-foundation.org>,
Vlastimil Babka <vbabka@...e.cz>, <linux-mm@...ck.org>,
<linux-kernel@...r.kernel.org>, <pratik.r.sampat@...il.com>
Subject: Re: [PATCH v3 0/6] percpu: partial chunk depopulation
On Fri, Apr 16, 2021 at 02:18:10PM +0000, Dennis Zhou wrote:
> Hello,
>
> On Fri, Apr 16, 2021 at 06:26:15PM +0530, Pratik Sampat wrote:
> > Hello Roman,
> >
> > I've tried the v3 patch series on a POWER9 and an x86 KVM setup.
> >
> > My results of the percpu_test are as follows:
> > Intel KVM 4CPU:4G
> > Vanilla 5.12-rc6
> > # ./percpu_test.sh
> > Percpu: 1952 kB
> > Percpu: 219648 kB
> > Percpu: 219648 kB
> >
> > 5.12-rc6 + with patchset applied
> > # ./percpu_test.sh
> > Percpu: 2080 kB
> > Percpu: 219712 kB
> > Percpu: 72672 kB
> >
> > I'm able to see improvement comparable to that of what you're see too.
> >
> > However, on POWERPC I'm unable to reproduce these improvements with the patchset in the same configuration
> >
> > POWER9 KVM 4CPU:4G
> > Vanilla 5.12-rc6
> > # ./percpu_test.sh
> > Percpu: 5888 kB
> > Percpu: 118272 kB
> > Percpu: 118272 kB
> >
> > 5.12-rc6 + with patchset applied
> > # ./percpu_test.sh
> > Percpu: 6144 kB
> > Percpu: 119040 kB
> > Percpu: 119040 kB
> >
> > I'm wondering if there's any architectural specific code that needs plumbing
> > here?
> >
>
> There shouldn't be. Can you send me the percpu_stats debug output before
> and after?
Btw, sidelined chunks are not listed in the debug output. It was actually on my
to-do list, looks like I need to prioritize it a bit.
>
> > I will also look through the code to find the reason why POWER isn't
> > depopulating pages.
> >
> > Thank you,
> > Pratik
> >
> > On 08/04/21 9:27 am, 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,
> > > so that sometimes there are several GB's of memory wasted.
> > >
> > > 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 solves 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: 135552 kB
> > >
> > > So the total size of the percpu memory was reduced by more than 3.5 times.
> > >
> > > v3:
> > > - introduced pcpu_check_chunk_hint()
> > > - fixed a bug related to the hint check
> > > - minor cosmetic changes
> > > - s/pretends/fixes (cc Vlastimil)
> > >
> > > v2:
> > > - depopulated chunks are sidelined
> > > - depopulation happens in the reverse order
> > > - depopulate list made per-chunk type
> > > - better results due to better heuristics
> > >
> > > v1:
> > > - 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 (6):
> > > percpu: fix a comment about the chunks ordering
> > > percpu: split __pcpu_balance_workfn()
> > > percpu: make pcpu_nr_empty_pop_pages per chunk type
> > > percpu: generalize pcpu_balance_populated()
> > > percpu: factor out pcpu_check_chunk_hint()
> > > percpu: implement partial chunk depopulation
> > >
> > > mm/percpu-internal.h | 4 +-
> > > mm/percpu-stats.c | 9 +-
> > > mm/percpu.c | 306 +++++++++++++++++++++++++++++++++++--------
> > > 3 files changed, 261 insertions(+), 58 deletions(-)
> > >
> >
>
> Roman, sorry for the delay. I'm looking to apply this today to for-5.14.
Great, thanks!
Powered by blists - more mailing lists