From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-1.1 required=3.0 tests=DKIMWL_WL_HIGH,DKIM_SIGNED, DKIM_VALID,DKIM_VALID_AU,MAILING_LIST_MULTI,SPF_HELO_NONE,SPF_PASS autolearn=no autolearn_force=no version=3.4.0 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by smtp.lore.kernel.org (Postfix) with ESMTP id 8913DC2BB1D for ; Fri, 17 Apr 2020 23:22:53 +0000 (UTC) Received: from kanga.kvack.org (kanga.kvack.org [205.233.56.17]) by mail.kernel.org (Postfix) with ESMTP id 4B815221EA for ; Fri, 17 Apr 2020 23:22:53 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (1024-bit key) header.d=kernel.org header.i=@kernel.org header.b="cZ0Bvbed" DMARC-Filter: OpenDMARC Filter v1.3.2 mail.kernel.org 4B815221EA Authentication-Results: mail.kernel.org; dmarc=fail (p=none dis=none) header.from=kernel.org Authentication-Results: mail.kernel.org; spf=pass smtp.mailfrom=owner-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix) id C0B7C8E0003; Fri, 17 Apr 2020 19:22:52 -0400 (EDT) Received: by kanga.kvack.org (Postfix, from userid 40) id BBD138E0001; Fri, 17 Apr 2020 19:22:52 -0400 (EDT) X-Delivered-To: int-list-linux-mm@kvack.org Received: by kanga.kvack.org (Postfix, from userid 63042) id AD1888E0003; Fri, 17 Apr 2020 19:22:52 -0400 (EDT) X-Delivered-To: linux-mm@kvack.org Received: from forelay.hostedemail.com (smtprelay0029.hostedemail.com [216.40.44.29]) by kanga.kvack.org (Postfix) with ESMTP id 92EDC8E0001 for ; Fri, 17 Apr 2020 19:22:52 -0400 (EDT) Received: from smtpin08.hostedemail.com (10.5.19.251.rfc1918.com [10.5.19.251]) by forelay04.hostedemail.com (Postfix) with ESMTP id 5012552B3 for ; Fri, 17 Apr 2020 23:22:52 +0000 (UTC) X-FDA: 76718924184.08.map49_705756b570905 X-HE-Tag: map49_705756b570905 X-Filterd-Recvd-Size: 2443 Received: from mail.kernel.org (mail.kernel.org [198.145.29.99]) by imf49.hostedemail.com (Postfix) with ESMTP for ; Fri, 17 Apr 2020 23:22:51 +0000 (UTC) Received: from kicinski-fedora-pc1c0hjn.dhcp.thefacebook.com (unknown [163.114.132.4]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.kernel.org (Postfix) with ESMTPSA id B659C221EA; Fri, 17 Apr 2020 23:22:50 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=default; t=1587165771; bh=ftdKWGgpIDLZDqr/mtlNo4/49vEIAWuOveNytV1igpc=; h=Date:From:To:Cc:Subject:In-Reply-To:References:From; b=cZ0BvbedqipSYOEP06wf+4Wk0rHhX3n7O/h+J7aROxs03yXlcfHFdrb7woubqPx6g 0trl37tPnerWYr7m3ao1JycRQI7QFYAeRQFOFlawPRqSRobYUm8wbD/0A44lY3u+s9 c69OVXWHRvSQhao25faEPxiEbtuZJ/hNKYij0L3M= Date: Fri, 17 Apr 2020 16:22:48 -0700 From: Jakub Kicinski To: Michal Hocko Cc: akpm@linux-foundation.org, linux-mm@kvack.org, kernel-team@fb.com, tj@kernel.org, hannes@cmpxchg.org, chris@chrisdown.name, cgroups@vger.kernel.org Subject: Re: [PATCH 3/3] mm: automatically penalize tasks with high swap use Message-ID: <20200417162248.415ff51e@kicinski-fedora-pc1c0hjn.dhcp.thefacebook.com> In-Reply-To: <20200417073716.GG26707@dhcp22.suse.cz> References: <20200417010617.927266-1-kuba@kernel.org> <20200417010617.927266-4-kuba@kernel.org> <20200417073716.GG26707@dhcp22.suse.cz> MIME-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit X-Bogosity: Ham, tests=bogofilter, spamicity=0.000000, version=1.2.4 Sender: owner-linux-mm@kvack.org Precedence: bulk X-Loop: owner-majordomo@kvack.org List-ID: On Fri, 17 Apr 2020 09:37:16 +0200 Michal Hocko wrote: > On Thu 16-04-20 18:06:17, Jakub Kicinski wrote: > > Add a memory.swap.high knob, which functions in a similar way > > to memory.high, but with a less steep slope. > > This really begs for more details. What does "similar way to > memory.high" mean? Because my first thought would be that the swap usage > will be throttled and kept at the swap.high level. From a quick look at > the patch you only do throttling. There is no swap space reclaim to keep > the usage at the level. So unless I am missing something this is very > confusing and it doesn't really fit into high limit semantic. The new knob does influence mem_cgroup_swap_full(), but you're right, the analogy is not strong enough, I'll rephrase. > This changelog also doesn't describe any usecase. Will do.