From owner-freebsd-arm@freebsd.org Wed Aug 15 00:43:55 2018 Return-Path: Delivered-To: freebsd-arm@mailman.ysv.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2610:1c1:1:606c::19:1]) by mailman.ysv.freebsd.org (Postfix) with ESMTP id 749F6106C38D for ; Wed, 15 Aug 2018 00:43:55 +0000 (UTC) (envelope-from marklmi@yahoo.com) Received: from sonic316-9.consmr.mail.gq1.yahoo.com (sonic316-9.consmr.mail.gq1.yahoo.com [98.137.69.33]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (Client did not present a certificate) by mx1.freebsd.org (Postfix) with ESMTPS id DDA0A70885 for ; Wed, 15 Aug 2018 00:43:54 +0000 (UTC) (envelope-from marklmi@yahoo.com) X-YMail-OSG: hE6gXY8VM1kYeFrg3fz5nhzIQu81f5bt45fCpAABkkct53ePdeauIbjaJ_aEq78 nfwYwXUi4NAihDv8I8MFN4yruzsZwpSbK4CGzmf5lkxKFSNIENObH.RRM7j1WTRluQXQBa1M2SjW zysDoZ8xkp1m7xa_R.7OXwrrtFC_NoIGMoNysj4b0VtwIMt3gfIXESd5BsTe9._u9Zb_FhiJyDIf uXprwO5UXo1ebAvowA4jngrTDPxw8SKwXfdQQTFRRlrOdJvzFKHTcnez2jQY1K9mSdLGuadl.oDz 5bl21SK61pAGuO1WSDc822WiyVrF7RLIX.4YpgidsRTASEz5rxOoVQCfM16VyQZEAvlloy6hk.cz wN9YO4v_q5cztzUCG716w4eHZsHx7pWrbGdBz9jLY5Mus2.nwKvBcMvtesxmLVCOACbMsszFX0z9 8jY4qjgNADfiBn5eQ6ycZUrMlgOnVctQ94zijNAcsxMZnIFjWb6EZSKrR7Zqqmi5NVUnF.N89UE1 qLhycZgbp2jKOmUWriOiwBLwWZ_k3snzok2Hw_7gkIbrw1cKWWafMDHT22UqVHzOy01.pailI5FE pP7Th314tjuntsVeUmZZc76MyWSkxU_aDzBn.BHFUjUaltBVKJKCOqLz13X7XU1ej_T0yNKhhvM2 VisxxIE7Nd.vP9XRSOKMER5iFwG5HW4Fhe9QNT4ydrsTdbGdVXR_3VT1z981HZeM_xCtuv.FMnkJ u_c2ve48nzbtxawa22pmbIE_IRD0_sYUbNc8wXS1YaGAavcOQcK3aTjnwXw9LnJrx40loWwYWWtE Iny6VTbpaWCI.lltJbiUm4JtQxiM5DcgaVprzq_3pbIeE2AFXnd4iL88zlMFXGhN2BaiMH_nnLbk b99jxvwISrYensHrj.zhyVdl7pf4FBvfbzPmr6YJq02469fQ0LVLhyZAFRKVDDS5ZYNocsGWkLqU y4.3rfN6kRhS2Q_hnmH0IwV9dQQBRDY_JBUDyJ6gBpr2fWDycgrSVZzc9eoup5m5ya8EkQ6bsafW YliAkwYrU Received: from sonic.gate.mail.ne1.yahoo.com by sonic316.consmr.mail.gq1.yahoo.com with HTTP; Wed, 15 Aug 2018 00:43:48 +0000 Received: from ip70-189-131-151.lv.lv.cox.net (EHLO [192.168.0.105]) ([70.189.131.151]) by smtp430.mail.gq1.yahoo.com (Oath Hermes SMTP Server) with ESMTPA ID 851f19f8a99653398ed6315c46cb039b; Wed, 15 Aug 2018 00:33:38 +0000 (UTC) From: Mark Millard Message-Id: Mime-Version: 1.0 (Mac OS X Mail 11.5 \(3445.9.1\)) Subject: Re: RPI3 swap experiments (grace under pressure) Date: Tue, 14 Aug 2018 17:33:37 -0700 In-Reply-To: Cc: bob prohaska , freebsd-arm , Mark Johnston To: Warner Losh References: <20180809033735.GJ30738@phouka1.phouka.net> <20180809175802.GA32974@www.zefox.net> <20180812173248.GA81324@phouka1.phouka.net> <20180812224021.GA46372@www.zefox.net> <20180813021226.GA46750@www.zefox.net> <0D8B9A29-DD95-4FA3-8F7D-4B85A3BB54D7@yahoo.com> <20180813185350.GA47132@www.zefox.net> <20180814014226.GA50013@www.zefox.net> X-Mailer: Apple Mail (2.3445.9.1) Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: quoted-printable X-Content-Filtered-By: Mailman/MimeDel 2.1.27 X-BeenThere: freebsd-arm@freebsd.org X-Mailman-Version: 2.1.27 Precedence: list List-Id: "Porting FreeBSD to ARM processors." List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 15 Aug 2018 00:43:55 -0000 On 2018-Aug-14, at 4:50 PM, Warner Losh wrote: > On Mon, Aug 13, 2018 at 7:42 PM, bob prohaska > wrote: > [Altered subject, philosophical question] > On Mon, Aug 13, 2018 at 01:05:38PM -0700, Mark Millard wrote: > >=20 > > Here there is architecture choice and goals/primary > > contexts. FreeBSD is never likely to primarily target > > anything with a workload like buildworld buildkernel > > on hardware like rpi3's and rpi2 V1.1's and > > Pine64+ 2GB's and so on. > >=20 >=20 > I understand that the RPi isn't a primary platform for FreeBSD. > But, decent performance under overload seems like a universal > problem that's always worth solving, whether for a computer or > an office. The exact goals might vary, but coping with too much > to do and not enough to do it with is humanity's oldest puzzle.=20 >=20 > Maybe I should ask what the goals of the OOMA process serve. > I always thought an OS's goals were along the lines of: > 1. maintain control > 2. get the work done > 3. remain responsive >=20 > Simplistically, one can view the VM system as a producer of dirty = pages, and a cleaner of dirty pages. These happen at different rates, = but usually are closely matched. We're normally able to launder enough = pages to satisfy the need for new pages from the VM system (since clean = pages can just be thrown away w/o any loss of data). The problem happens = when we put a large load onto the creation side with a build. This = generates a lot of dirty pages, and we have to flush the writes of the = dirty pages quickly to keep up. When the backing store has time-varying = write rates that vary substantially, we run into problems. Just an FYI example comparison/contrast: For a buildworld buildkernel example with vm.pageout_oom_seq=3D12 v_free_count: 7773, v_inactive_count: 1 Aug 12 09:30:13 pine64 kernel: pid 80573 (c++), uid 0, was killed: out = of swap space without any "Mark J." messages such as: waited 4s for async swap write waited 4s for swap buffer waited 4s for async swap write waited 4s for async swap write waited 4s for async swap write The code uses 3s as the starting point for such reports as I remember, so shorter times would not have been reported. The context was a Pine64+ 2GB. A from-scratch buildworld buildkernel with vm.pageout_oom_seq=3D120 also reported no "waited" messages but had no kills. Note: I got that little "4s" block during a later poudriere bulk during or a few seconds after the devel/cmake build. So far that is the only report that I've seen from Mark J.'s reporting code for the Pine64+ 2G context that I have access to. Not even the later about 14.5 hr devel/llvm60 build reported such messages. poudreire bulk was running one job at a time but allowed each job to use all 4 cores. > . . . =3D=3D=3D Mark Millard marklmi at yahoo.com ( dsl-only.net went away in early 2018-Mar)