Received: by 2002:a05:6a10:f3d0:0:0:0:0 with SMTP id a16csp2823907pxv; Sat, 3 Jul 2021 22:45:51 -0700 (PDT) X-Google-Smtp-Source: ABdhPJzruXHCbrfThNw2TejIUMyXU1m0CDTOp8Y4cFjtGaUavdA4JAz1jNaLrswwBAmFICWJwPhF X-Received: by 2002:aa7:da0c:: with SMTP id r12mr4100073eds.49.1625377551560; Sat, 03 Jul 2021 22:45:51 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1625377551; cv=none; d=google.com; s=arc-20160816; b=BTYjSPvAklrzf44e/XMiz4iR7EnPp8qH2jYPEjf3ZxToTcBazfO9RsjzylBhCoI7uJ 1x2KUNhObc7Us3/AP5qer8fmV1yZEvxIb3WCEcoEuJE7iaIyhxI8CQshLeow1qXGB596 kclZdHjyLa74s9DbettIhAoVC344a24H2923s4MJ2zeXmqnOny+6u7Gb+nOHRZT08MrX qdEt9ozsdMa+ZohHyPNG+81DW2pybLwKDnY5nrZRv1k4dL62/gCw9oID0VOcuua97hIt KYzS69JGRcTGuZW+jvJVPyfB3mPLZYlSqyTdvUqyFYscD+kjiN18PQHRxEbFuolET1Xh ZiQg== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=list-id:precedence:content-transfer-encoding:mime-version :user-agent:references:in-reply-to:date:cc:to:from:subject :message-id:dkim-signature; bh=tQDFYgcse0ZvVcR93IN8xChVF4xxvoDwC2XLbwYwuJ8=; b=an7Y+a8s9XWCZWN7AuAXMRv2YB1A9S89TmBfM5yVyO6TGdXVHUlRjaymdg9VpyeGZ+ VoRKIi3vYdFfCKiESp5h09XdSPi7HF1YMRnu76pjqjCbGi9r+j4BGV9vDIgajcPI4OXE ehroKTXIqt5FgoSibF06z3W94Rd0RYTVCOMui+ePV+LBKpxNQ+GeeAcwIhXrmqL/fYEV IgY/5Jrln59frlsJWyeFZVTexPuJjGcA6rtSqmT8j+9B/fg5LH9o5C3tcg3F+7pcKgxh esySKHSnYr3UnqRrI0alWf2cBztClNzxX+xsUcKA48qpYndrjoBD9WGjJ6/x5KQGW6Yd VfAw== ARC-Authentication-Results: i=1; mx.google.com; dkim=pass header.i=@gmx.net header.s=badeba3b8450 header.b=ebQRJe3u; spf=pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org; dmarc=fail (p=NONE sp=NONE dis=NONE) header.from=gmx.de Return-Path: Received: from vger.kernel.org (vger.kernel.org. [23.128.96.18]) by mx.google.com with ESMTP id e1si7755286edr.289.2021.07.03.22.45.28; Sat, 03 Jul 2021 22:45:51 -0700 (PDT) Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18; Authentication-Results: mx.google.com; dkim=pass header.i=@gmx.net header.s=badeba3b8450 header.b=ebQRJe3u; spf=pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org; dmarc=fail (p=NONE sp=NONE dis=NONE) header.from=gmx.de Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S229573AbhGDFlF (ORCPT + 99 others); Sun, 4 Jul 2021 01:41:05 -0400 Received: from mout.gmx.net ([212.227.15.15]:45593 "EHLO mout.gmx.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S229476AbhGDFlE (ORCPT ); Sun, 4 Jul 2021 01:41:04 -0400 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=gmx.net; s=badeba3b8450; t=1625377076; bh=arnfTZBwNvGLZwUtAVTdYmP0q7oaOHvftfLOkK6UrMo=; h=X-UI-Sender-Class:Subject:From:To:Cc:Date:In-Reply-To:References; b=ebQRJe3uhk7ZOncnqg5UtLNZe8Hgb8E0rcQbsvbZTjz+3r3sDDEkoZe+rFLFuEQbS 8fCCkq2Ze1MxbanSkCzULyPRgI4N/a/4DSUqh6sUma03Dv8PTmJ8kjCv31tb3FDgPC IFYkpopu/AhlO0bsdkavMcgdC9eBTtDtt1Lzq81A= X-UI-Sender-Class: 01bb95c1-4bf8-414a-932a-4f6e2808ef9c Received: from homer.fritz.box ([185.146.50.156]) by mail.gmx.net (mrgmx005 [212.227.17.190]) with ESMTPSA (Nemesis) id 1MGQjH-1lyaR43q29-00GnzP; Sun, 04 Jul 2021 07:37:56 +0200 Message-ID: Subject: Re: [RFC v2 00/34] SLUB: reduce irq disabled scope and make it RT compatible From: Mike Galbraith To: Sebastian Andrzej Siewior , Vlastimil Babka Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org, Christoph Lameter , David Rientjes , Pekka Enberg , Joonsoo Kim , Thomas Gleixner , Mel Gorman , Jesper Dangaard Brouer , Peter Zijlstra , Jann Horn Date: Sun, 04 Jul 2021 07:37:53 +0200 In-Reply-To: References: <20210609113903.1421-1-vbabka@suse.cz> <20210702182944.lqa7o2a25to6czju@linutronix.de> <891dc24e38106f8542f4c72831d52dc1a1863ae8.camel@gmx.de> Content-Type: text/plain; charset="UTF-8" User-Agent: Evolution 3.34.4 MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable X-Provags-ID: V03:K1:ujmV8DUSfYq29RjSzDm+4tehRJmb1Jp0Xc+uEIVqkVXI7973u+f Y/OnAdOjGbApFZPSG35k1LdGlDqOVbRBStpqX7FiX+u6SfCf0gG7hF01Uyd/e+9VselZOhS hX/jKNWOeGO2uAJ5N0bXHHX+t/SGDkJnG9FCAtFJPWJOXVpJ7AXEtSVCr/d/oD/YQzrSu9w LgGAaQwhVkyBSHsxNfcuQ== X-Spam-Flag: NO X-UI-Out-Filterresults: notjunk:1;V03:K0:QakDQzSDsy4=:k8wHEv5FrCCPFlbOsFYT5U vWBNKVxTKV9qh5rQEYlEnO4wbciT+RrKR4ZgRH9WX9LykCD1uSF5/Cc6AIlv7YkYu5sXV2OZm hd+cOT5Cy0PLjV7P7P0l7U1RTih0EsQBvkrqxW5hJEpppaJe+HygV+J5w1V5vviyH0SVTyWva 1WdJgPxmROTI0l8S0plQSBVitwBf1qYPzyOIwUAO4uveczxNLSsIa0yuYLgq3lbOzHL0TEThq mZ40EqkUBVDxdfr2zJNHuaHbc7l26UmeTnfoO+Gw4zfxz3Xufmux9H6/tDT1NPrFDucf/zQIO wrJwbKJmKZw2nRzw220J9HfeqDCZpnCwkV0pjzJRqbYtJ33I1HZ2q+Y+lPePg8nw1H++J5j4Y fquBFbqdXlQChpttRCoCISZJqlKa2k4qrMlkOjXeFyCWBJ4g0zFbfkOFP3K0Fr1nnNkvbpsCd lpelKHMDeNYjmiw6ba1D6J86IhdJc9fq60E3C24oCbIsUy77kUWDcQv/GuGpdZiva57cmGx5y hzpHcJJi/LGVwSVw2kp4GSiTRggW2dkJpI4bDAZ8AnHsgIJN68qa/poJZhQCWR9PHF4mTaH4C HW5FCofYZsOrw46iP4FFoqED+TPffwTCOhd1y8Y39fjF4eBDA4RY6Gyer4/2PUcBF3BmT2aSO /bFheuz5wA3cpZIKo81ZsMfkwRjbi4b6n+wWmS1tGyP6H9rAF/dVkwiESpSvVSceu45DEOco7 O9fdf0bsJ7DNQNWzdKuGY2TYBBTLW3Oh+WGbppaKDi9K2Xh2Oq10lwD+ncB+k5jj5yX9Kfh7u diFydRAvvqm1eSko8O9Ch8VvTdp3dXGgxBYV/nyaW7P5ebdVMs4Icx6ypS5wXjk6RpSEq9x+m Rkuph4g9zP18cstf7bKZIGojKymr1L9ttqnPNprofzVIOLKojXgJNQ7i14eXQ7EnHKQJdl3px Xwi3us7l0/cogcBorWxcgLIu3XWKgJnC/XcnQ+ITGSvIfDgqQO+1qEGHRF++fVPPfaXpo2iX2 0Yr6QlePUoU8sCqWnHvReL3IbdlHCPMgX+cP9gBFbOfMrMkhwa3DUdcClhfIZfR6puHUeR1dF z4MaY6HDGW25mrbSvFzadErf287MD4iMqW/ Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Sat, 2021-07-03 at 17:47 +0200, Mike Galbraith wrote: > On Sat, 2021-07-03 at 09:24 +0200, Mike Galbraith wrote: > > It also appears to be saying that there's something RT specific to > > stare at in addition to the list_lock business. > > The what is ___slab_alloc() consuming 3.9% CPU in tip-rt-slub whereas > it consumes < 1% in both tip-rt (sans slub patches) and tip-slub. > > The why remains to ponder. Ignoring odd distribution in the profile (red herring whackable via prefetch games), and removing perf/debug options from the picture, the remaining RT specific cost is just that of forced slow path. For hackbench in my little box, it adds up to right at 3%. -Mike