[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <54a4d626-faed-ad86-f3c4-5e725986bd29@google.com>
Date: Thu, 15 Aug 2024 20:14:44 -0700 (PDT)
From: David Rientjes <rientjes@...gle.com>
To: Andrew Morton <akpm@...ux-foundation.org>
cc: Yuanchu Xie <yuanchu@...gle.com>, David Hildenbrand <david@...hat.com>,
"Aneesh Kumar K.V" <aneesh.kumar@...ux.ibm.com>,
Khalid Aziz <khalid.aziz@...cle.com>, Henry Huang <henry.hj@...group.com>,
Yu Zhao <yuzhao@...gle.com>, Dan Williams <dan.j.williams@...el.com>,
Gregory Price <gregory.price@...verge.com>,
Huang Ying <ying.huang@...el.com>, Lance Yang <ioworker0@...il.com>,
Randy Dunlap <rdunlap@...radead.org>,
Muhammad Usama Anjum <usama.anjum@...labora.com>,
Kalesh Singh <kaleshsingh@...gle.com>, Wei Xu <weixugc@...gle.com>,
Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
"Rafael J. Wysocki" <rafael@...nel.org>,
Johannes Weiner <hannes@...xchg.org>, Michal Hocko <mhocko@...nel.org>,
Roman Gushchin <roman.gushchin@...ux.dev>,
Muchun Song <muchun.song@...ux.dev>, Shuah Khan <shuah@...nel.org>,
Yosry Ahmed <yosryahmed@...gle.com>, Matthew Wilcox <willy@...radead.org>,
Sudarshan Rajagopalan <quic_sudaraja@...cinc.com>,
Kairui Song <kasong@...cent.com>, "Michael S. Tsirkin" <mst@...hat.com>,
Vasily Averin <vasily.averin@...ux.dev>, Nhat Pham <nphamcs@...il.com>,
Miaohe Lin <linmiaohe@...wei.com>, Qi Zheng <zhengqi.arch@...edance.com>,
Abel Wu <wuyun.abel@...edance.com>,
"Vishal Moola (Oracle)" <vishal.moola@...il.com>,
Kefeng Wang <wangkefeng.wang@...wei.com>, linux-kernel@...r.kernel.org,
linux-mm@...ck.org, cgroups@...r.kernel.org,
linux-kselftest@...r.kernel.org
Subject: Re: [PATCH v3 0/7] mm: workingset reporting
On Tue, 13 Aug 2024, Andrew Morton wrote:
> On Tue, 13 Aug 2024 09:56:11 -0700 Yuanchu Xie <yuanchu@...gle.com> wrote:
>
> > This patch series provides workingset reporting of user pages in
> > lruvecs, of which coldness can be tracked by accessed bits and fd
> > references.
>
> Very little reviewer interest. I wonder why. Will Google be the only
> organization which finds this useful?
>
Although also from Google, I'm optimistic that others will find this very
useful. It's implemented in a way that is intended to be generally useful
for multiple use cases, including user defined policy for proactive
reclaim. The cited sample userspace implementation is intended to
demonstrate how this insight can be put into practice.
Insight into the working set of applications, particularly on multi-tenant
systems, has derived significant memory savings for Google over the past
decade. The introduction of MGLRU into the upstream kernel has allowed
this information to be derived in a much more efficient manner, presented
here, that should make upstreaming of this insight much more palatable.
This insight into working set will only become more critical going forward
with memory tiered systems.
Nothing here is specific to Google; in fact, we apply the insight into
working set in very different ways across our fleets.
> > Benchmarks
> > ==========
> > Ghait Ouled Amar Ben Cheikh has implemented a simple "reclaim everything
> > colder than 10 seconds every 40 seconds" policy and ran Linux compile
> > and redis from the phoronix test suite. The results are in his repo:
> > https://github.com/miloudi98/WMO
>
> I'd suggest at least summarizing these results here in the [0/N]. The
> Linux kernel will probably outlive that URL!
>
Fully agreed that this would be useful for including in the cover letter.
The results showing the impact of proactive reclaim using insight into
working set is impressive for multi-tenant systems. Having very
comparable performance for kernbench with a fraction of the memory usage
shows the potential for proactive reclaim and without the dependency on
direct reclaim or throttling of the application itself.
This is one of several benchmarks that we are running and we'll be
expanding upon this with cotenancy, user defined latency senstivity per
job, extensions for insight into memory re-access, and in-guest use cases.
Powered by blists - more mailing lists