RE: [PATCH v8 13/13] Documentation/x86: Update resctrl.rst for new features
From: Moger, Babu
Date: Wed Nov 23 2022 - 18:02:58 EST
[AMD Official Use Only - General]
Hi Reinette,
> -----Original Message-----
> From: Reinette Chatre <reinette.chatre@xxxxxxxxx>
> Sent: Tuesday, November 22, 2022 6:26 PM
> To: Moger, Babu <Babu.Moger@xxxxxxx>; corbet@xxxxxxx;
> tglx@xxxxxxxxxxxxx; mingo@xxxxxxxxxx; bp@xxxxxxxxx
> Cc: fenghua.yu@xxxxxxxxx; dave.hansen@xxxxxxxxxxxxxxx; x86@xxxxxxxxxx;
> hpa@xxxxxxxxx; paulmck@xxxxxxxxxx; akpm@xxxxxxxxxxxxxxxxxxxx;
> quic_neeraju@xxxxxxxxxxx; rdunlap@xxxxxxxxxxxxx;
> damien.lemoal@xxxxxxxxxxxxxxxxxx; songmuchun@xxxxxxxxxxxxx;
> peterz@xxxxxxxxxxxxx; jpoimboe@xxxxxxxxxx; pbonzini@xxxxxxxxxx;
> chang.seok.bae@xxxxxxxxx; pawan.kumar.gupta@xxxxxxxxxxxxxxx;
> jmattson@xxxxxxxxxx; daniel.sneddon@xxxxxxxxxxxxxxx; Das1, Sandipan
> <Sandipan.Das@xxxxxxx>; tony.luck@xxxxxxxxx; james.morse@xxxxxxx;
> linux-doc@xxxxxxxxxxxxxxx; linux-kernel@xxxxxxxxxxxxxxx;
> bagasdotme@xxxxxxxxx; eranian@xxxxxxxxxx
> Subject: Re: [PATCH v8 13/13] Documentation/x86: Update resctrl.rst for new
> features
>
> Hi Babu,
>
> On 11/4/2022 1:01 PM, Babu Moger wrote:
> ...
>
> > @@ -464,6 +539,26 @@ Memory bandwidth domain is L3 cache.
> >
> > MB:<cache_id0>=bw_MBps0;<cache_id1>=bw_MBps1;...
> >
> > +Slow Memory Bandwidth Allocation (SMBA)
> > +---------------------------------------
> > +AMD hardware support Slow Memory Bandwidth Allocation (SMBA) feature.
>
> How about
> AMD hardware supports the Slow Memory Bandwidth Allocation (SMBA)
> feature.
> or
> AMD hardware supports Slow Memory Bandwidth Allocation (SMBA).
Sure.
>
> > +Currently, CXL.memory is the only supported "slow" memory device.
>
> What does "Currently" mean here? If there is a plan for changes, could that be
> shared? Otherwise maybe just remove it: "CXL.memory is the only supported
> "slow" memory device."
There is no change of plan. I will remove "Currently"
>
> > +With the support of SMBA, the hardware enables bandwidth allocation
> > +on the slow memory devices. If there are multiple such devices in the
> > +system, the throttling logic groups all the slow sources together and
> > +applies the limit on them as a whole.
> > +
> > +The presence of SMBA (with CXL.memory) is independent of slow memory
> > +devices presence. If there is no such devices on the system, then
>
> Maybe "is no such device" or "are no such devices"?
It should be "If there are no such devices". Will correct it.
>
> > +setting the configuring SMBA will have no impact on the performance
>
> "setting the configuring SMBA" is hard to parse. How about just "configuring
> SMBA"?
Sure.
Thanks
Babu
<<attachment: winmail.dat>>