[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <7887abff-8118-4064-8cb6-3f4af8cc4b2a@intel.com>
Date: Wed, 22 May 2024 14:12:20 -0700
From: Reinette Chatre <reinette.chatre@...el.com>
To: Tony Luck <tony.luck@...el.com>, Fenghua Yu <fenghua.yu@...el.com>, Maciej
Wieczor-Retman <maciej.wieczor-retman@...el.com>, Peter Newman
<peternewman@...gle.com>, James Morse <james.morse@....com>, Babu Moger
<babu.moger@....com>, Drew Fustini <dfustini@...libre.com>, Dave Martin
<Dave.Martin@....com>
CC: <x86@...nel.org>, <linux-kernel@...r.kernel.org>,
<patches@...ts.linux.dev>
Subject: Re: [PATCH v18 07/17] x86/resctrl: Prepare for new Sub-NUMA (SNC)
cluster monitor files
Hi Tony,
Please note in the subject (and many places in this series) the
text "Sub-NUMA (SNC)" is used. Is that intentional? Other places
it reads "Sub-NUMA Cluster (SNC)".
On 5/15/2024 3:23 PM, Tony Luck wrote:
> When SNC is enabled monitoring data is collected at the SNC node
> granularity, but must be reported at L3-cache granularity for
> backwards compatibility in addition to reporting at the node
> level.
>
> Add a mon_display_scope field to the rdt_resource structure to track
> reporting scope. Default is for non-SNC systems where both scopes
> are the same.
Just to confirm ... the reporting scope needs to be superset of
the "collecting"(?) scope. Is this something that is implicitly enforced?
Reinette
Powered by blists - more mailing lists