Re: [PATCH v7 24/24] x86/resctrl: Introduce interface to modify assignment states of the groups

[Moger, Babu]

Hi Reinette,

On 10/3/2024 9:17 PM, Reinette Chatre wrote:
> Hi Babu,
>
> On 10/3/24 6:11 PM, Moger, Babu wrote:
> > Hi Reinette,
> >
> > On 10/2/2024 1:19 PM, Reinette Chatre wrote:
> > > Hi Babu,
> > >
> > > On 9/27/24 10:47 AM, Moger, Babu wrote:
> > > > On 9/19/2024 12:59 PM, Reinette Chatre wrote:
> > > > > On 9/4/24 3:21 PM, Babu Moger wrote:
> > >
> > > > > > v7: Simplified the parsing (strsep(&token, "//") in rdtgroup_mbm_assign_control_write().
> > > > > >        Added mutex lock in rdtgroup_mbm_assign_control_write() while processing.
> > > > > >        Renamed rdtgroup_find_grp to rdtgroup_find_grp_by_name.
> > > > > >        Fixed rdtgroup_str_to_mon_state to return error for invalid flags.
> > > > > >        Simplified the calls rdtgroup_assign_cntr by merging few functions earlier.
> > > > > >        Removed ABMC reference in FS code.
> > > > > >        Reinette commented about handling the combination of flags like 'lt_' and '_lt'.
> > > > > >        Not sure if we need to change the behaviour here. Processed them sequencially right now.
> > > > > >        Users have the liberty to pass the flags. Restricting it might be a problem later.
> > > > >
> > > > > Could you please give an example of what problem may be encountered later? An assignment
> > > > > like "domain=_lt" seems like a contradiction to me since user space essentially asks
> > > > > for "None of the MBM events" as well as "MBM total event" and "MBM local event".
> > > >
> > > > I agree it is contradiction. But user is the one who decides to do that. I think we should allow it. Also, there is some value to it as well.
> > > >
> > > > "domain=_lt" This will also reset the counters if the total and local events are assigned earlier this action.
> > >
> > > The last sentence is not clear to me. Could you please elaborate what
> > > you mean with "are assigned earlier this action"?
> >
> > I think I confused you here. "domain=_lt" is equivalent to "domain=lt".  My reasoning is handling all the combination in the code adds code complexity and leave it the user what he wants to do.
>
> hmmm ... and how about "domain=lt_"? Do you think this should also be equivalent to
> "domain=lt" or perhaps an expectation that counters should be assigned to the two events
> and then immediately unassigned?

Yes. "domain=lt_" should be "domain=lt".

> Giving user such flexibility may be interpreted as the assignment seen as acting
> sequentially through the flags provided. Ideally the interface should behave in
> a predictable way if the goal is to provide flexibility to the user.

My only concern is adding the check now and reverting it back later.
Basically process the flags sequentially and don't differentiate between 
the flags. I feel it fits the predictable behavior. No?

--
- Babu Moger