[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20151218204915.GA30427@amt.cnet>
Date: Fri, 18 Dec 2015 18:49:15 -0200
From: Marcelo Tosatti <mtosatti@...hat.com>
To: Christoph Lameter <cl@...ux.com>
Cc: Fenghua Yu <fenghua.yu@...el.com>,
"H. Peter Anvin" <hpa@...ux.intel.com>,
Ingo Molnar <mingo@...e.hu>,
Thomas Gleixner <tglx@...utronix.de>,
Tony Luck <tony.luck@...el.com>,
Ravi V Shankar <ravi.v.shankar@...el.com>,
Peter Zijlstra <peterz@...radead.org>,
Tejun Heo <tj@...nel.org>,
linux-kernel <linux-kernel@...r.kernel.org>, x86 <x86@...nel.org>
Subject: Re: [PATCH V16 00/11] x86: Intel Cache Allocation Technology Support
On Fri, Dec 18, 2015 at 11:45:29AM -0600, Christoph Lameter wrote:
> On Thu, 17 Dec 2015, Fenghua Yu wrote:
>
> > Intel Cache allocation support:
> >
> > Cache allocation patches adds a cgroup subsystem to support the new
> > Cache Allocation feature found in future Intel Xeon Intel processors.
> > Cache Allocation is a sub-feature with in Resource Director
> > Technology(RDT) feature. Current patches support only L3 cache
> > allocation.
> >
> > Cache Allocation provides a way for the Software (OS/VMM) to restrict
> > cache allocation to a defined 'subset' of cache which may be overlapping
> > with other 'subsets'. This feature is used when a thread is allocating
> > a cache line ie when pulling new data into the cache.
> >
> > Threads are associated with a CLOS(Class of service). OS specifies the
> > CLOS of a thread by writing the IA32_PQR_ASSOC MSR during context
> > switch. The cache capacity associated with CLOS 'n' is specified by
> > writing to the IA32_L3_MASK_n MSR.
>
> Could you also support another low level interface where a task (or
> process) can set the CLOS id itself if it has CAP_SYS_NICE.
Hi Christoph,
Do you have a proposal for an interface?
> Plus some way
> for the supervisor to directly control the IA32_L3_MASK_n MSR?
What you mean supervisor? Hypervisor or root user?
> Is there a way to see these values for debugging purposes?
Yes, from userspace, wrmsr and rdmsr.
> We tightly control processes and bind them to processors. cpusets are
> often a too high level instrument at that level.
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists