From: Yosry Ahmed <yosryahmed@google.com> To: Johannes Weiner <hannes@cmpxchg.org>, Michal Hocko <mhocko@kernel.org>, Shakeel Butt <shakeelb@google.com>, Andrew Morton <akpm@linux-foundation.org>, David Rientjes <rientjes@google.com>, Roman Gushchin <roman.gushchin@linux.dev> Cc: cgroups@vger.kernel.org, Tejun Heo <tj@kernel.org>, Linux-MM <linux-mm@kvack.org>, Yu Zhao <yuzhao@google.com>, Wei Xu <weixugc@google.com>, Greg Thelen <gthelen@google.com>, Chen Wandun <chenwandun@huawei.com> Subject: [RFC] Add swappiness argument to memory.reclaim Date: Mon, 16 May 2022 15:29:42 -0700 [thread overview] Message-ID: <CAJD7tkbDpyoODveCsnaqBBMZEkDvshXJmNdbk51yKSNgD7aGdg@mail.gmail.com> (raw) The discussions on the patch series [1] to add memory.reclaim has shown that it is desirable to add an argument to control the type of memory being reclaimed by invoked proactive reclaim using memory.reclaim. I am proposing adding a swappiness optional argument to the interface. If set, it overwrites vm.swappiness and per-memcg swappiness. This provides a way to enforce user policy on a stateless per-reclaim basis. We can make policy decisions to perform reclaim differently for tasks of different app classes based on their individual QoS needs. It also helps for use cases when particularly page cache is high and we want to mainly hit that without swapping out. The interface would be something like this (utilizing the nested-keyed interface we documented earlier): $ echo "200M swappiness=30" > memory.reclaim Looking forward to hearing thoughts about this before I go ahead and send a patch. [1]https://lore.kernel.org/lkml/20220331084151.2600229-1-yosryahmed@google.com/
WARNING: multiple messages have this Message-ID (diff)
From: Yosry Ahmed <yosryahmed-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org> To: Johannes Weiner <hannes-druUgvl0LCNAfugRpC6u6w@public.gmane.org>, Michal Hocko <mhocko-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>, Shakeel Butt <shakeelb-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>, Andrew Morton <akpm-de/tnXTf+JLsfHDXvbKv3WD2FQJk+8+b@public.gmane.org>, David Rientjes <rientjes-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>, Roman Gushchin <roman.gushchin-fxUVXftIFDnyG1zEObXtfA@public.gmane.org> Cc: cgroups-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, Tejun Heo <tj-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>, Linux-MM <linux-mm-Bw31MaZKKs3YtjvyW6yDsg@public.gmane.org>, Yu Zhao <yuzhao-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>, Wei Xu <weixugc-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>, Greg Thelen <gthelen-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org>, Chen Wandun <chenwandun-hv44wF8Li93QT0dZR+AlfA@public.gmane.org> Subject: [RFC] Add swappiness argument to memory.reclaim Date: Mon, 16 May 2022 15:29:42 -0700 [thread overview] Message-ID: <CAJD7tkbDpyoODveCsnaqBBMZEkDvshXJmNdbk51yKSNgD7aGdg@mail.gmail.com> (raw) The discussions on the patch series [1] to add memory.reclaim has shown that it is desirable to add an argument to control the type of memory being reclaimed by invoked proactive reclaim using memory.reclaim. I am proposing adding a swappiness optional argument to the interface. If set, it overwrites vm.swappiness and per-memcg swappiness. This provides a way to enforce user policy on a stateless per-reclaim basis. We can make policy decisions to perform reclaim differently for tasks of different app classes based on their individual QoS needs. It also helps for use cases when particularly page cache is high and we want to mainly hit that without swapping out. The interface would be something like this (utilizing the nested-keyed interface we documented earlier): $ echo "200M swappiness=30" > memory.reclaim Looking forward to hearing thoughts about this before I go ahead and send a patch. [1]https://lore.kernel.org/lkml/20220331084151.2600229-1-yosryahmed-hpIqsD4AKlfQT0dZR+AlfA@public.gmane.org/
next reply other threads:[~2022-05-16 22:30 UTC|newest] Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top 2022-05-16 22:29 Yosry Ahmed [this message] 2022-05-16 22:29 ` [RFC] Add swappiness argument to memory.reclaim Yosry Ahmed 2022-05-17 6:56 ` Michal Hocko 2022-05-17 6:56 ` Michal Hocko 2022-05-17 18:06 ` Yosry Ahmed 2022-05-17 18:06 ` Yosry Ahmed 2022-05-17 20:06 ` Johannes Weiner 2022-05-17 20:06 ` Johannes Weiner 2022-05-19 5:44 ` Wei Xu 2022-05-19 5:44 ` Wei Xu 2022-05-19 8:51 ` Michal Hocko 2022-05-19 8:51 ` Michal Hocko 2022-05-19 15:29 ` Wei Xu 2022-05-19 15:29 ` Wei Xu 2022-05-19 18:24 ` Yosry Ahmed 2022-05-19 18:24 ` Yosry Ahmed 2022-05-17 16:05 ` Roman Gushchin 2022-05-17 16:05 ` Roman Gushchin 2022-05-17 18:13 ` Yosry Ahmed 2022-05-17 18:13 ` Yosry Ahmed 2022-05-17 19:49 ` Roman Gushchin 2022-05-17 19:49 ` Roman Gushchin 2022-05-17 20:11 ` Yosry Ahmed 2022-05-17 20:11 ` Yosry Ahmed 2022-05-17 20:45 ` Roman Gushchin 2022-05-17 20:45 ` Roman Gushchin 2022-05-19 5:17 ` Wei Xu 2022-05-19 5:17 ` Wei Xu
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=CAJD7tkbDpyoODveCsnaqBBMZEkDvshXJmNdbk51yKSNgD7aGdg@mail.gmail.com \ --to=yosryahmed@google.com \ --cc=akpm@linux-foundation.org \ --cc=cgroups@vger.kernel.org \ --cc=chenwandun@huawei.com \ --cc=gthelen@google.com \ --cc=hannes@cmpxchg.org \ --cc=linux-mm@kvack.org \ --cc=mhocko@kernel.org \ --cc=rientjes@google.com \ --cc=roman.gushchin@linux.dev \ --cc=shakeelb@google.com \ --cc=tj@kernel.org \ --cc=weixugc@google.com \ --cc=yuzhao@google.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: linkBe sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes, see mirroring instructions on how to clone and mirror all data and code used by this external index.