[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <16989547-8209-8428-80a2-910cf667885f@intel.com>
Date: Tue, 27 Feb 2018 13:33:55 -0800
From: Reinette Chatre <reinette.chatre@...el.com>
To: Thomas Gleixner <tglx@...utronix.de>
Cc: fenghua.yu@...el.com, tony.luck@...el.com, gavin.hindman@...el.com,
vikas.shivappa@...ux.intel.com, dave.hansen@...el.com,
mingo@...hat.com, hpa@...or.com, x86@...nel.org,
linux-kernel@...r.kernel.org
Subject: Re: [RFC PATCH V2 13/22] x86/intel_rdt: Support schemata write -
pseudo-locking core
Hi Thomas,
On 2/27/2018 11:52 AM, Reinette Chatre wrote:
> On 2/27/2018 2:36 AM, Thomas Gleixner wrote:
>> Let's assume its real,
>> so you could do the following:
>>
>> mkdir group <- acquires closid
>> echo locksetup > mode <- Creates 'lockarea' file
>> echo L2:0 > lockarea
>> echo 'L2:0=0xf' > schemata
>> echo locked > mode <- locks down all files, does the lock setup
>> and drops closid
>>
>> That would solve quite some of the other issues as well. Hmm?
>
> At this time the resource group, represented by a resctrl directory, is
> tightly associated with the closid. I'll take a closer look at what it
> will take to separate them.
>
> Could you please elaborate on the purpose of the "lockarea" file? It
> does seem to duplicate the information in the schemata written in the
> subsequent line.
>
> If we do go this route then it seems that there would be one
> pseudo-locked region per resource group, not multiple ones as I had in
> my examples above.
Actually, this need not be true. It could be possible for administrator
to pseudo-lock two regions at once. For example,
mkdir group
echo locksetup > mode
echo 'L2:0=0xf;1=0xf' > schemata
This could have two pseudo-locked regions associated with a single
resource group. This does complicate the usage of the "size" file even
more though since the plan was to have a single "size" file associated
with a resource group it is not intuitive how it should describe
multiple pseudo-locked regions. I added the "size" file originally to
help users of the pseudo-locking interface where a single pseudo-locked
region existed in a directory. All information to compute the size
themselves are available to users, perhaps I can add pseudo-code to
compute the size from available information to the documentation?
Reinette
Powered by blists - more mailing lists