From owner-svn-src-head@freebsd.org Wed Aug 12 00:22:08 2020 Return-Path: Delivered-To: svn-src-head@mailman.nyi.freebsd.org Received: from mx1.freebsd.org (mx1.freebsd.org [IPv6:2610:1c1:1:606c::19:1]) by mailman.nyi.freebsd.org (Postfix) with ESMTP id A8FB63BAB09; Wed, 12 Aug 2020 00:22:08 +0000 (UTC) (envelope-from cse.cem@gmail.com) Received: from mail-ot1-f48.google.com (mail-ot1-f48.google.com [209.85.210.48]) (using TLSv1.3 with cipher TLS_AES_128_GCM_SHA256 (128/128 bits) key-exchange X25519 server-signature RSA-PSS (4096 bits) server-digest SHA256 client-signature RSA-PSS (2048 bits) client-digest SHA256) (Client CN "smtp.gmail.com", Issuer "GTS CA 1O1" (verified OK)) by mx1.freebsd.org (Postfix) with ESMTPS id 4BR9PX2cvCz4FHM; Wed, 12 Aug 2020 00:22:08 +0000 (UTC) (envelope-from cse.cem@gmail.com) Received: by mail-ot1-f48.google.com with SMTP id t7so629877otp.0; Tue, 11 Aug 2020 17:22:08 -0700 (PDT) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:mime-version:references:in-reply-to:reply-to :from:date:message-id:subject:to:cc; bh=wEWF5O77Ga/rQVJcE4tL3KyRO+dod94J4/+WTFxNl30=; b=C4Ab8FrAUgVWsFzcmZjnagW0jNr2aJWOsBXw0Z6CqFrQ1dOPR34ond5k+uQjBODK4j hTXZrqkhSftYDnLF5iUNgCsHyTLiwYLv2tewGkl2HHdIn3v7mrPLTk31HH0xwULB7z8+ g4yTN0qHTHnDzP3jQD3naU9GRG/OxGN/LXT6wew2GNHe2AvNSG5tPDDCe7OCzG5Rze/V vzOP1eV67GsRvQHeZkREd3XBWUAY2uSOUZpNEFSlOLtk0/Zz4q9L6XxkRk0Zu3mzs+C9 YGqEVsSHs1B9sWUDKB0oay7FTxtUIN+rEmIWRMYjC/6nonliFA9a9w+DXXaLtnnEL+5r T1Iw== X-Gm-Message-State: AOAM532B3VKOb8lZiThYnoNJtvIPcEDnZan0wUz9ikV+t1mFCdPOF1kf Qu7Aa+tU07slaM1QglQT+l2W3x8i X-Google-Smtp-Source: ABdhPJyXg2ly1F47xu1xBtNMI5TUz37fhJDit08KWo8hjBTDoRose/YdEEoXNZ3Q0CQ4xD4q2tCflg== X-Received: by 2002:a05:6830:60f:: with SMTP id w15mr7217494oti.85.1597191727025; Tue, 11 Aug 2020 17:22:07 -0700 (PDT) Received: from mail-oi1-f169.google.com (mail-oi1-f169.google.com. [209.85.167.169]) by smtp.gmail.com with ESMTPSA id l128sm140819oib.4.2020.08.11.17.22.06 (version=TLS1_3 cipher=TLS_AES_128_GCM_SHA256 bits=128/128); Tue, 11 Aug 2020 17:22:06 -0700 (PDT) Received: by mail-oi1-f169.google.com with SMTP id u63so293190oie.5; Tue, 11 Aug 2020 17:22:06 -0700 (PDT) X-Received: by 2002:aca:5703:: with SMTP id l3mr5305694oib.48.1597191726280; Tue, 11 Aug 2020 17:22:06 -0700 (PDT) MIME-Version: 1.0 References: <202008112037.07BKbjsL056699@repo.freebsd.org> <20200811213213.GT2551@kib.kiev.ua> <20200811223100.GC77647@raichu> In-Reply-To: <20200811223100.GC77647@raichu> Reply-To: cem@freebsd.org From: Conrad Meyer Date: Tue, 11 Aug 2020 17:21:55 -0700 X-Gmail-Original-Message-ID: Message-ID: Subject: Re: svn commit: r364129 - head/sys/vm To: Mark Johnston , Konstantin Belousov Cc: src-committers , svn-src-all , svn-src-head Content-Type: text/plain; charset="UTF-8" X-Rspamd-Queue-Id: 4BR9PX2cvCz4FHM X-Spamd-Bar: ---- Authentication-Results: mx1.freebsd.org; none X-Spamd-Result: default: False [-4.00 / 15.00]; ASN(0.00)[asn:15169, ipnet:209.85.128.0/17, country:US]; TAGGED_FROM(0.00)[]; REPLY(-4.00)[] X-BeenThere: svn-src-head@freebsd.org X-Mailman-Version: 2.1.33 Precedence: list List-Id: SVN commit messages for the src tree for head/-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 12 Aug 2020 00:22:08 -0000 Done in r364134. On Tue, Aug 11, 2020 at 3:31 PM Mark Johnston wrote: > > On Tue, Aug 11, 2020 at 03:21:31PM -0700, Conrad Meyer wrote: > > Hi Konstantin, Mark (raised the same question), > > > > On Tue, Aug 11, 2020 at 2:32 PM Konstantin Belousov wrote: > > > > > > On Tue, Aug 11, 2020 at 08:37:45PM +0000, Conrad Meyer wrote: > > > > Author: cem > > > > Date: Tue Aug 11 20:37:45 2020 > > > > New Revision: 364129 > > > > URL: https://svnweb.freebsd.org/changeset/base/364129 > > > > > > > > Log: > > > > Add support for multithreading the inactive queue pageout within a domain. > > > > ... > > > > @@ -2488,7 +2488,7 @@ vm_page_zone_import(void *arg, void **store, int cnt, > > > > * main purpose is to replenish the store of free pages. > > > > */ > > > > if (vmd->vmd_severeset || curproc == pageproc || > > > > - !_vm_domain_allocate(vmd, VM_ALLOC_NORMAL, cnt)) > > > > + !_vm_domain_allocate(vmd, VM_ALLOC_SYSTEM, cnt)) > > > > > > Why this change needed ? > > > > The change was inherited from Jeff, along with the rest of it. I > > don't know why he changed it, but it does seem orthogonal to the rest > > of the revision. This part is nonessential as far as I know, and > > could be backed out. > > To me it doesn't make sense. The difference between VM_ALLOC_NORMAL and > _SYSTEM is that they use different thresholds for the free page count > before deciding whether to continue the allocation. The _NORMAL > threshold is higher than the _SYSTEM threshold, but both are smaller > than the "severe" threshold at which we set vmd_severeset. In other > words, if the free page count is such that a _NORMAL allocation would > fail but a _SYSTEM allocation would succeed, then vmd_severeset would be > set and we'd never get to the _vmd_domain_allocate() call to begin with. > > So, I think this part of the change should be reverted. Even if the > analysis is incorrect, it's logically separate from the rest of the > diff. Prior to r355003 it made more sense, but per that commit it can > be harmful to populate the per-CPU page caches when the system is > severely short on free pages, so I would disagree with it anyway without > more testing.