From: Johannes Weiner <hannes@cmpxchg.org>
To: Alex Shi <alex.shi@linux.alibaba.com>
Cc: cgroups@vger.kernel.org, linux-kernel@vger.kernel.org,
linux-mm@kvack.org, akpm@linux-foundation.org,
mgorman@techsingularity.net, tj@kernel.org, hughd@google.com,
khlebnikov@yandex-team.ru, daniel.m.jordan@oracle.com,
yang.shi@linux.alibaba.com, willy@infradead.org,
shakeelb@google.com, "Michal Hocko" <mhocko@kernel.org>,
"Vladimir Davydov" <vdavydov.dev@gmail.com>,
"Roman Gushchin" <guro@fb.com>,
"Chris Down" <chris@chrisdown.name>,
"Thomas Gleixner" <tglx@linutronix.de>,
"Vlastimil Babka" <vbabka@suse.cz>, "Qian Cai" <cai@lca.pw>,
"Andrey Ryabinin" <aryabinin@virtuozzo.com>,
"Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>,
"Jérôme Glisse" <jglisse@redhat.com>,
"Andrea Arcangeli" <aarcange@redhat.com>,
"David Rientjes" <rientjes@google.com>,
"Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>,
swkhack <swkhack@gmail.com>,
"Potyra, Stefan" <Stefan.Potyra@elektrobit.com>,
"Mike Rapoport" <rppt@linux.vnet.ibm.com>,
"Stephen Rothwell" <sfr@canb.auug.org.au>,
"Colin Ian King" <colin.king@canonical.com>,
"Jason Gunthorpe" <jgg@ziepe.ca>,
"Mauro Carvalho Chehab" <mchehab+samsung@kernel.org>,
"Peng Fan" <peng.fan@nxp.com>,
"Nikolay Borisov" <nborisov@suse.com>,
"Ira Weiny" <ira.weiny@intel.com>,
"Kirill Tkhai" <ktkhai@virtuozzo.com>,
"Yafang Shao" <laoar.shao@gmail.com>,
"Wei Yang" <richard.weiyang@linux.alibaba.com>
Subject: Re: [PATCH v8 03/10] mm/lru: replace pgdat lru_lock with lruvec lock
Date: Tue, 14 Apr 2020 12:36:58 -0400 [thread overview]
Message-ID: <20200414163658.GB136578@cmpxchg.org> (raw)
In-Reply-To: <42d5c2cb-3019-993f-eba7-33a1d69ef699@linux.alibaba.com>
On Tue, Apr 14, 2020 at 04:19:01PM +0800, Alex Shi wrote:
>
>
> 在 2020/4/14 上午2:07, Johannes Weiner 写道:
> > But isolation actually needs to lock out charging, or it would operate
> > on the wrong list:
> >
> > isolation: commit_charge:
> > if (TestClearPageLRU(page))
> > page->mem_cgroup = new
> > // page is still physically on
> > // the root_mem_cgroup's LRU. We're
> > // updating the wrong list:
> > memcg = page->mem_cgroup
> > spin_lock(memcg->lru_lock)
> > del_page_from_lru_list(page, memcg)
> > spin_unlock(memcg->lru_lock)
> >
> > lrucare really is a mess. Even before this patch series, it makes
> > things tricky and subtle and error prone.
> >
> > The only reason we're doing it is for when there is swapping without
> > swap tracking, in which case swap reahadead needs to put pages on the
> > LRU but cannot charge them until we have a faulting vma later.
> >
> > But it's not clear how practical such a configuration is. Both memory
> > and swap are shared resources, and isolation isn't really effective
> > when you restrict access to memory but then let workloads swap freely.
> >
> > Plus, the overhead of tracking is tiny - 512k per G of swap (0.04%).
> >
> > Maybe we should just delete MEMCG_SWAP and unconditionally track swap
> > entry ownership when the memory controller is enabled. I don't see a
> > good reason not to, and it would simplify the entire swapin path, the
> > LRU locking, and the page->mem_cgroup stabilization rules.
>
> Hi Johannes,
>
> I think what you mean here is to keep swap_cgroup id even it was swaped,
> then we read back the page from swap disk, we don't need to charge it.
> So all other memcg charge are just happens on non lru list, thus we have
> no isolation required in above awkward scenario.
We don't need to change how swap recording works, we just need to
always do it when CONFIG_MEMCG && CONFIG_SWAP.
We can uncharge the page once it's swapped out. The only difference is
that with a swap record, we know who owned the page and can charge
readahead pages right awya, before setting PageLRU; whereas without a
record, we read pages onto the LRU, and then wait until we hit a page
fault with an mm to charge. That's why we have this lrucare mess.
next prev parent reply other threads:[~2020-04-14 16:37 UTC|newest]
Thread overview: 29+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-01-16 3:04 [PATCH v8 00/10] per lruvec lru_lock for memcg Alex Shi
2020-01-16 3:05 ` [PATCH v8 01/10] mm/vmscan: remove unnecessary lruvec adding Alex Shi
2020-01-16 3:05 ` [PATCH v8 02/10] mm/memcg: fold lock_page_lru into commit_charge Alex Shi
2020-01-16 3:05 ` [PATCH v8 03/10] mm/lru: replace pgdat lru_lock with lruvec lock Alex Shi
2020-01-16 21:52 ` Johannes Weiner
2020-01-19 11:32 ` Alex Shi
2020-01-20 12:58 ` Alex Shi
2020-01-21 16:00 ` Johannes Weiner
2020-01-22 12:01 ` Alex Shi
2020-01-22 18:31 ` Johannes Weiner
2020-04-13 10:48 ` Alex Shi
2020-04-13 18:07 ` Johannes Weiner
2020-04-14 4:52 ` Alex Shi
2020-04-14 16:31 ` Johannes Weiner
2020-04-15 13:42 ` Alex Shi
2020-04-16 8:01 ` Alex Shi
2020-04-16 15:28 ` Johannes Weiner
2020-04-16 17:47 ` Shakeel Butt
2020-04-17 13:18 ` Alex Shi
2020-04-17 14:39 ` Alex Shi
2020-04-14 8:19 ` Alex Shi
2020-04-14 16:36 ` Johannes Weiner [this message]
2020-01-16 3:05 ` [PATCH v8 04/10] mm/lru: introduce the relock_page_lruvec function Alex Shi
2020-01-16 3:05 ` [PATCH v8 05/10] mm/mlock: optimize munlock_pagevec by relocking Alex Shi
2020-01-16 3:05 ` [PATCH v8 06/10] mm/swap: only change the lru_lock iff page's lruvec is different Alex Shi
2020-01-16 3:05 ` [PATCH v8 07/10] mm/pgdat: remove pgdat lru_lock Alex Shi
2020-01-16 3:05 ` [PATCH v8 08/10] mm/lru: revise the comments of lru_lock Alex Shi
2020-01-16 3:05 ` [PATCH v8 09/10] mm/lru: add debug checking for page memcg moving Alex Shi
2020-01-16 3:05 ` [PATCH v8 10/10] mm/memcg: add debug checking in lock_page_memcg Alex Shi
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20200414163658.GB136578@cmpxchg.org \
--to=hannes@cmpxchg.org \
--cc=Stefan.Potyra@elektrobit.com \
--cc=aarcange@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=alex.shi@linux.alibaba.com \
--cc=aneesh.kumar@linux.ibm.com \
--cc=aryabinin@virtuozzo.com \
--cc=cai@lca.pw \
--cc=cgroups@vger.kernel.org \
--cc=chris@chrisdown.name \
--cc=colin.king@canonical.com \
--cc=daniel.m.jordan@oracle.com \
--cc=guro@fb.com \
--cc=hughd@google.com \
--cc=ira.weiny@intel.com \
--cc=jgg@ziepe.ca \
--cc=jglisse@redhat.com \
--cc=khlebnikov@yandex-team.ru \
--cc=kirill.shutemov@linux.intel.com \
--cc=ktkhai@virtuozzo.com \
--cc=laoar.shao@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mchehab+samsung@kernel.org \
--cc=mgorman@techsingularity.net \
--cc=mhocko@kernel.org \
--cc=nborisov@suse.com \
--cc=peng.fan@nxp.com \
--cc=richard.weiyang@linux.alibaba.com \
--cc=rientjes@google.com \
--cc=rppt@linux.vnet.ibm.com \
--cc=sfr@canb.auug.org.au \
--cc=shakeelb@google.com \
--cc=swkhack@gmail.com \
--cc=tglx@linutronix.de \
--cc=tj@kernel.org \
--cc=vbabka@suse.cz \
--cc=vdavydov.dev@gmail.com \
--cc=willy@infradead.org \
--cc=yang.shi@linux.alibaba.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).