From: Brice Goglin <Brice.Goglin@inria.fr>
To: Keith Busch <keith.busch@intel.com>,
Jonathan Cameron <jonathan.cameron@huawei.com>
Cc: "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
"linux-acpi@vger.kernel.org" <linux-acpi@vger.kernel.org>,
"linux-mm@kvack.org" <linux-mm@kvack.org>,
Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
Rafael Wysocki <rafael@kernel.org>,
"Hansen, Dave" <dave.hansen@intel.com>,
"Williams, Dan J" <dan.j.williams@intel.com>
Subject: Re: [PATCHv4 10/13] node: Add memory caching attributes
Date: Tue, 12 Feb 2019 09:11:03 +0100 [thread overview]
Message-ID: <854e892c-0c0d-6ab8-bc83-3c6b462bcf72@inria.fr> (raw)
In-Reply-To: <20190211152303.GA4525@localhost.localdomain>
Le 11/02/2019 à 16:23, Keith Busch a écrit :
> On Sun, Feb 10, 2019 at 09:19:58AM -0800, Jonathan Cameron wrote:
>> On Sat, 9 Feb 2019 09:20:53 +0100
>> Brice Goglin <Brice.Goglin@inria.fr> wrote:
>>
>>> Hello Keith
>>>
>>> Could we ever have a single side cache in front of two NUMA nodes ? I
>>> don't see a way to find that out in the current implementation. Would we
>>> have an "id" and/or "nodemap" bitmask in the sidecache structure ?
>> This is certainly a possible thing for hardware to do.
>>
>> ACPI IIRC doesn't provide any means of representing that - your best
>> option is to represent it as two different entries, one for each of the
>> memory nodes. Interesting question of whether you would then claim
>> they were half as big each, or the full size. Of course, there are
>> other possible ways to get this info beyond HMAT, so perhaps the interface
>> should allow it to be exposed if available?
> HMAT doesn't do this, but I want this interface abstracted enough from
> HMAT to express whatever is necessary.
>
> The CPU cache is the closest existing exported attributes to this,
> and they provide "shared_cpu_list". To that end, I can export a
> "shared_node_list", though previous reviews strongly disliked multi-value
> sysfs entries. :(
>
> Would shared-node symlinks capture the need, and more acceptable?
As a user-space guy reading these files/symlinks, I would prefer reading
a bitmask just like we do for CPU cache "cpumap" or CPU "siblings" files
(or sibling_list).
Reading a directory and looking for dentries matching "foo%d" is far
less convenient in C. If all these files are inside a dedicated
subdirectory, it's better but still not as easy.
Brice
next prev parent reply other threads:[~2019-02-12 8:11 UTC|newest]
Thread overview: 51+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-01-16 17:57 [PATCHv4 00/13] Heterogeneuos memory node attributes Keith Busch
2019-01-16 17:57 ` [PATCHv4 01/13] acpi: Create subtable parsing infrastructure Keith Busch
2019-01-16 17:57 ` [PATCHv4 02/13] acpi: Add HMAT to generic parsing tables Keith Busch
2019-01-16 17:57 ` [PATCHv4 03/13] acpi/hmat: Parse and report heterogeneous memory Keith Busch
2019-01-17 11:00 ` Rafael J. Wysocki
2019-01-16 17:57 ` [PATCHv4 04/13] node: Link memory nodes to their compute nodes Keith Busch
2019-01-17 11:26 ` Rafael J. Wysocki
2019-01-16 17:57 ` [PATCHv4 05/13] Documentation/ABI: Add new node sysfs attributes Keith Busch
2019-01-17 11:41 ` Rafael J. Wysocki
2019-01-18 20:42 ` Keith Busch
2019-01-18 21:08 ` Dan Williams
2019-01-19 9:01 ` Greg Kroah-Hartman
2019-01-19 16:56 ` Dan Williams
2019-01-20 16:19 ` Rafael J. Wysocki
2019-01-20 17:34 ` Dan Williams
2019-01-21 9:54 ` Rafael J. Wysocki
2019-01-20 16:16 ` Rafael J. Wysocki
2019-01-22 16:36 ` Keith Busch
2019-01-22 16:51 ` Rafael J. Wysocki
2019-01-22 16:54 ` Rafael J. Wysocki
2019-01-18 11:21 ` Jonathan Cameron
2019-01-18 16:35 ` Dan Williams
2019-01-16 17:57 ` [PATCHv4 06/13] acpi/hmat: Register processor domain to its memory Keith Busch
2019-01-17 12:11 ` Rafael J. Wysocki
2019-01-17 17:01 ` Dan Williams
2019-01-16 17:57 ` [PATCHv4 07/13] node: Add heterogenous memory access attributes Keith Busch
2019-01-17 15:03 ` Rafael J. Wysocki
2019-01-17 15:41 ` Greg Kroah-Hartman
2019-01-16 17:57 ` [PATCHv4 08/13] Documentation/ABI: Add node performance attributes Keith Busch
2019-01-17 15:09 ` Rafael J. Wysocki
2019-01-16 17:58 ` [PATCHv4 09/13] acpi/hmat: Register " Keith Busch
2019-01-17 15:21 ` Rafael J. Wysocki
2019-01-16 17:58 ` [PATCHv4 10/13] node: Add memory caching attributes Keith Busch
2019-01-17 16:00 ` Rafael J. Wysocki
2019-02-09 8:20 ` Brice Goglin
2019-02-10 17:19 ` Jonathan Cameron
2019-02-11 15:23 ` Keith Busch
2019-02-12 8:11 ` Brice Goglin [this message]
2019-02-12 8:49 ` Jonathan Cameron
2019-02-12 17:31 ` Keith Busch
2019-01-16 17:58 ` [PATCHv4 11/13] Documentation/ABI: Add node cache attributes Keith Busch
2019-01-17 16:25 ` Rafael J. Wysocki
2019-01-16 17:58 ` [PATCHv4 12/13] acpi/hmat: Register memory side " Keith Busch
2019-01-17 17:42 ` Rafael J. Wysocki
2019-01-16 17:58 ` [PATCHv4 13/13] doc/mm: New documentation for memory performance Keith Busch
2019-01-17 12:58 ` [PATCHv4 00/13] Heterogeneuos memory node attributes Balbir Singh
2019-01-17 15:44 ` Keith Busch
2019-01-18 13:16 ` Balbir Singh
2019-01-17 18:18 ` Jonathan Cameron
2019-01-17 19:47 ` Keith Busch
2019-01-18 11:12 ` Jonathan Cameron
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=854e892c-0c0d-6ab8-bc83-3c6b462bcf72@inria.fr \
--to=brice.goglin@inria.fr \
--cc=dan.j.williams@intel.com \
--cc=dave.hansen@intel.com \
--cc=gregkh@linuxfoundation.org \
--cc=jonathan.cameron@huawei.com \
--cc=keith.busch@intel.com \
--cc=linux-acpi@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=rafael@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).