From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-it1-f198.google.com (mail-it1-f198.google.com [209.85.166.198]) by kanga.kvack.org (Postfix) with ESMTP id 530496B7D27 for ; Thu, 6 Dec 2018 18:49:21 -0500 (EST) Received: by mail-it1-f198.google.com with SMTP id n124so2653335itb.7 for ; Thu, 06 Dec 2018 15:49:21 -0800 (PST) Received: from ale.deltatee.com (ale.deltatee.com. [207.54.116.67]) by mx.google.com with ESMTPS id s2si1090126itb.115.2018.12.06.15.49.20 for (version=TLS1_2 cipher=ECDHE-RSA-CHACHA20-POLY1305 bits=256/256); Thu, 06 Dec 2018 15:49:20 -0800 (PST) References: <20181205001544.GR2937@redhat.com> <42006749-7912-1e97-8ccd-945e82cebdde@intel.com> <20181205021334.GB3045@redhat.com> <20181205175357.GG3536@redhat.com> <20181206192050.GC3544@redhat.com> <20181206223935.GG3544@redhat.com> <935fc14d-91f2-bc2a-f8b5-665e4145e148@deltatee.com> <5e6c87d5-e4ef-12e7-32bf-c163f7ff58d7@intel.com> From: Logan Gunthorpe Message-ID: Date: Thu, 6 Dec 2018 16:48:57 -0700 MIME-Version: 1.0 In-Reply-To: <5e6c87d5-e4ef-12e7-32bf-c163f7ff58d7@intel.com> Content-Type: text/plain; charset=utf-8 Content-Language: en-CA Content-Transfer-Encoding: 7bit Subject: Re: [RFC PATCH 00/14] Heterogeneous Memory System (HMS) and hbind() Sender: owner-linux-mm@kvack.org List-ID: To: Dave Hansen , Jerome Glisse Cc: linux-mm@kvack.org, Andrew Morton , linux-kernel@vger.kernel.org, "Rafael J . Wysocki" , Matthew Wilcox , Ross Zwisler , Keith Busch , Dan Williams , Haggai Eran , Balbir Singh , "Aneesh Kumar K . V" , Benjamin Herrenschmidt , Felix Kuehling , Philip Yang , =?UTF-8?Q?Christian_K=c3=b6nig?= , Paul Blinzer , John Hubbard , Ralph Campbell , Michal Hocko , Jonathan Cameron , Mark Hairgrove , Vivek Kini , Mel Gorman , Dave Airlie , Ben Skeggs , Andrea Arcangeli , Rik van Riel , Ben Woodard , linux-acpi@vger.kernel.org On 2018-12-06 4:38 p.m., Dave Hansen wrote: > On 12/6/18 3:28 PM, Logan Gunthorpe wrote: >> I didn't think this was meant to describe actual real world performance >> between all of the links. If that's the case all of this seems like a >> pipe dream to me. > > The HMAT discussions (that I was a part of at least) settled on just > trying to describe what we called "sticker speed". Nobody had an > expectation that you *really* had to measure everything. > > The best we can do for any of these approaches is approximate things. Yes, though there's a lot of caveats in this assumption alone. Specifically with PCI: the bus may run at however many GB/s but P2P through a CPU's root complexes can slow down significantly (like down to MB/s). I've seen similar things across QPI: I can sometimes do P2P from PCI->QPI->PCI but the performance doesn't even come close to the sticker speed of any of those buses. I'm not sure how anyone is going to deal with those issues, but it does firmly place us in world view #2 instead of #1. But, yes, I agree exposing information like in #2 full out to userspace, especially through sysfs, seems like a nightmare and I don't see anything in HMS to help with that. Providing an API to ask for memory (or another resource) that's accessible by a set of initiators and with a set of requirements for capabilities seems more manageable. Logan