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;
Subject: Re: [RFC PATCH] topology: Represent clusters of CPUs within a die.
To:     Morten Rasmussen <morten.rasmussen@arm.com>,
        Jonathan Cameron <Jonathan.Cameron@Huawei.com>
Cc:     Len Brown <len.brown@intel.com>,
        Peter Zijlstra <peterz@infradead.org>,
        Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
        x86@kernel.org, guohanjun@huawei.com, linux-kernel@vger.kernel.org,
        linuxarm@huawei.com, linux-acpi@vger.kernel.org,
        Jerome Glisse <jglisse@redhat.com>,
        Sudeep Holla <sudeep.holla@arm.com>,
        Will Deacon <will@kernel.org>, valentin.schneider@arm.com,
        linux-arm-kernel@lists.infradead.org
References: <20201016152702.1513592-1-Jonathan.Cameron@huawei.com>
 <20201019103522.GK2628@hirez.programming.kicks-ass.net>
 <20201019123226.00006705@Huawei.com> <20201019131052.GC8004@e123083-lin>
 <20201019134157.00001c97@Huawei.com> <20201019141653.GE8004@e123083-lin>
From:   Brice Goglin <Brice.Goglin@inria.fr>
Autocrypt: addr=Brice.Goglin@inria.fr; prefer-encrypt=mutual; keydata=
 mQINBFNg91oBEADMfOyfz9iilNPe1Yy3pheXLf5O/Vpr+gFJoXcjA80bMeSWBf4on8Mt5Fg/
 jpVuNBhii0Zyq4Lip1I2ve+WQjfL3ixYQqvNRLgfw/FL0gNHSOe9dVFo0ol0lT+vu3AXOVmh
 AM4IrsOp2Tmt+w89Oyvu+xwHW54CJX3kXp4c7COz79A6OhbMEPQUreerTavSvYpH5pLY55WX
 qOSdjmlXD45yobQbMg9rFBy1BECrj4DJSpym/zJMFVnyC5yAq2RdPFRyvYfS0c491adD/iw9
 eFZY1XWj+WqLSW8zEejdl78npWOucfin7eAKvov5Bqa1MLGS/2ojVMHXJN0qpStpKcueV5Px
 igX8i4O4pPT10xCXZ7R6KIGUe1FE0N7MLErLvBF6AjMyiFHix9rBG0pWADgCQUUFjc8YBKng
 nwIKl39uSpk5W5rXbZ9nF3Gp/uigTBNVvaLO4PIDw9J3svHQwCB31COsUWS1QhoLMIQPdUkk
 GarScanm8i37Ut9G+nB4nLeDRYpPIVBFXFD/DROIEfLqOXNbGwOjDd5RWuzA0TNzJSeOkH/0
 qYr3gywjiE81zALO3UeDj8TaPAv3Dmu7SoI86Bl7qm6UOnSL7KQxZWuMTlU3BF3d+0Ly0qxv
 k1XRPrL58IyoHIgAVom0uUnLkRKHczdhGDpNzsQDJaO71EPp8QARAQABtCRCcmljZSBHb2ds
 aW4gPEJyaWNlLkdvZ2xpbkBpbnJpYS5mcj6JAjgEEwECACIFAlNg+aMCGwMGCwkIBwMCBhUI
 AgkKCwQWAgMBAh4BAheAAAoJEESRkPMjWr076RoQAJhJ1q5+wlHIf+YvM0N1V1hQyf+aL35+
 BPqxlyw4H65eMWIN/63yWhcxrLwNCdgY1WDWGoiW8KVCCHwJAmrXukFvXjsvShLQJavWRgKH
 eea12T9XtLc6qY/DEi2/rZvjOCKsMjnc1CYW71jbofaQP6lJsmC+RPWrnL/kjZyVrVrg7/Jo
 GemLmi/Ny7nLAOt6uL0MC/Mwld14Yud57Qz6VTDGSOvpNacbkJtcCwL3KZDBfSDnZtSbeclY
 srXoMnFXEJJjKJ6kcJrZDYPrNPkgFpSId/WKJ5pZBoRsKH/w2OdxwtXKCYHksMCiI4+4fVFD
 WlmVNYzW8ZKXjAstLh+xGABkLVXs+0WjvC67iTZBXTmbYJ5eodv8U0dCIR/dxjK9wxVKbIr2
 D+UVbGlfqUuh1zzL68YsOg3L0Xc6TQglKVl6RxX87fCU8ycIs9pMbXeRDoJohflo8NUDpljm
 zqGlZxBjvb40p37ReJ+VfjWqAvVh+6JLaMpeva/2K1Nvr9O/DOkSRNetrd86PslrIwz8yP4l
 FaeG0dUwdRdnToNz6E8lbTVOwximW+nwEqOZUs1pQNKDejruN7Xnorr7wVBfp6zZmFCcmlw9
 8pSMV3p85wg6nqJnBkQNTzlljycBvZLVvqc6hPOSXpXf5tjkuUVWgtbCc8TDEQFx8Phkgda6
 K1LNuQINBFNg91oBEADp3vwjw8tQBnNfYJNJMs6AXC8PXB5uApT1pJ0fioaXvifPNL6gzsGt
 AF53aLeqB7UXuByHr8Bmsz7BvwA06XfXXdyLQP+8Oz3ZnUpw5inDIzLpRbUuAjI+IjUtguIK
 AkU1rZNdCXMOqEwCaomRitwaiX9H7yiDTKCUaqx8yAuAQWactWDdyFii2FA7IwVlD/GBqMWV
 weZsMfeWgPumKB3jyElm1RpkzULrtKbu7MToMH2fmWqBtTkRptABkY7VEd8qENKJBZKJGisk
 Fk6ylp8VzZdwbAtEDDTGK00Vg4PZGiIGbQo8mBqbc63DY+MdyUEksTTu2gTcqZMm/unQUJA8
 xB4JrTAyljo/peIt6lsQa4+/eVolfKL1t1C3DY8f4wMoqnZORagnWA2oHsLsYKvcnqzA0QtY
 IIb1S1YatV+MNMFf3HuN7xr/jWlfdt59quXiOHU3qxIzXJo/OfC3mwNW4zQWJkG233UOf6YE
 rmrSaTIBTIWF8CxGY9iXPaJGNYSUa6R/VJS09EWeZgRz9Gk3h5AyDrdo5RFN9HNwOj41o0cj
 eLDF69092Lg5p5isuOqsrlPi5imHKcDtrXS7LacUI6H0c8onWoH9LuW99WznEtFgPJg++TAv
 f9M2x57Gzl+/nYTB5/Kpl1qdPPC91zUipiKbnF5f8bQpol0WC+ovmQARAQABiQIfBBgBAgAJ
 BQJTYPdaAhsMAAoJEESRkPMjWr074+0P/iEcN27dx3oBTzoeGEBhZUVQRZ7w4A61H/vW8oO8
 IPkZv9kFr5pCfIonmHEbBlg6yfjeHXwF5SF2ywWRKkRsFHpaFWywxqk9HWXu8cGR1pFsrwC3
 EdossuVbEFNmhjHvcAo11nJ7JFzPTEnlPjE6OY9tEDwl+kp1WvyXqNk9bosaX8ivikhmhB47
 7BA3Kv8uUE7UL6p7CBdqumaOFISi1we5PYE4P/6YcyhQ9Z2wH6ad2PpwAFNBwxSu+xCrVmaD
 skAwknf6UVPN3bt67sFAaVgotepx6SPhBuH4OSOxVHMDDLMu7W7pJjnSKzMcAyXmdjON05Sz
 SaILwfceByvHAnvcFh2pXK9U4E/SyWZDJEcGRRt79akzZxls52stJK/2Tsr0vKtZVAwogiaK
 uSp+m6BRQcVVhTo/Kq3E0tSnsTHFeIO6QFHKJCJv4FRE3Dmtz15lueihUBowsq9Hk+u3UiLo
 SmrMAZ6KgA4SQxB2p8/M53kNJl92HHc9nc//aCQDi1R71NyhtSx+6PyivoBkuaKYs+S4pHmt
 sFE+5+pkUNROtm4ExLen4N4OL6Kq85mWGf2f6hd+OWtn8we1mADjDtdnDHuv+3E3cacFJPP/
 wFV94ZhqvW4QcyBWcRNFA5roa7vcnu/MsCcBoheR0UdYsOnJoEpSZswvC/BGqJTkA2sf
Message-ID: <0190e18f-7a55-e1d6-b966-f7844a251609@inria.fr>
Date:   Mon, 19 Oct 2020 16:42:24 +0200
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:68.0) Gecko/20100101
 Thunderbird/68.12.0
MIME-Version: 1.0
In-Reply-To: <20201019141653.GE8004@e123083-lin>
Content-Type: text/plain; charset=utf-8
Content-Transfer-Encoding: 8bit
Content-Language: en-US
Precedence: bulk


Le 19/10/2020 à 16:16, Morten Rasmussen a écrit :
>
>>> If there is a provable benefit of having interconnect grouping
>>> information, I think it would be better represented by a distance matrix
>>> like we have for NUMA.
>> There have been some discussions in various forums about how to
>> describe the complexity of interconnects well enough to actually be
>> useful.  Those have mostly floundered on the immense complexity of
>> designing such a description in a fashion any normal software would actually
>> use.  +cc Jerome who raised some of this in the kernel a while back.
> I agree that representing interconnect details is hard. I had hoped that
> a distance matrix would be better than nothing and more generic than
> inserting extra group masks.
>

The distance matrix is indeed more precise, but would it scale to
tens/hundreds of core? When ACPI HMAT latency/bandwidth was added, there
were concerns that exposing the full matrix would be an issue for the
kernel (that's why only local latency/bandwidth is exposed n sysfs).
This was only for NUMA nodes/targets/initiators, you would have
significantly more cores than that.

Brice